AI Trustworthiness

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 133% on the four weeks before. 0.3% of all new papers.

Jul 6Week of Sep 21

Latest papers 228

Jul 28, 2026cs.RO

Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels

Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction. Because failures can cause immediate physical or operational harm, task completion alone does not establish trustworthiness. We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably under environmental and system variation while maintaining risk within acceptable bounds. We term this objective sustained safe success. Its supporting mechanisms are organized into four interdependent layers. The model layer generates task-competent action proposals with calibrated uncertainty and explicit safety preferences. The system layer realizes authorized actions dependably through integrated sensing, computation, control, hardware safeguards, fault containment, and fallback. The evidence layer substantiates bounded claims through evaluation, verification, validation, traceability, and structured assurance arguments. The deployment layer maintains claim validity through runtime monitoring, authority management, intervention, incident response, and controlled updates. Because assumptions and failures propagate across these layers, neither model capability, isolated safeguards, nor benchmark performance alone can establish end-to-end trustworthiness. Drawing on embodied AI, robotics, control, dependable computing, distributed systems, and autonomous driving, we further propose a non-normative hierarchy of trustworthiness levels. This hierarchy grades the strength of bounded deployment claims across task capability, safety, system assurance, operational governance, and supporting evidence, providing a basis for bounded deployment, comparative evaluation, research prioritization, and future standardization.

Xinyu Yang, Tianxing Chen, Honghao Su +38

Trustworthy Artificial Intelligence AI Trustworthiness Embodied Artificial Intelligence Intelligence

Jul 28, 2026cs.AI

Toward Standardized Cross-Vendor Agent Tool Trust Management in Autonomous Networks

Autonomous Network Levels 4-5 require AI agents to invoke tools across vendor boundaries without human oversight, yet existing management standards lack a standardized mechanism for cross-vendor trust visibility. When a tool from Vendor B is compromised, agents from Vendor A continue invoking it -- unaware of the trust degradation -- causing cascading service impact. We present AgentToolMO, a proposed 3GPP NRM information model for agent tool trust management. The model comprises: a formally defined trust state machine with provable graduated enforcement, damped cascade propagation with bounded convergence, cross-vendor trust notifications via existing Management Services (MnS) interfaces, and retroactive impact assessment through NRM dependency graph traversal. Simulation-based evaluation across multi-vendor topologies shows that standardized cross-vendor notifications reduce blast radius from hours-scale undetected propagation to near-real-time containment bounded by MnS notification delivery, with cascade convergence guaranteed in bounded iterations and sub-linear notification scaling across vendor domains. The framework operates within existing 3GPP management infrastructure, leverages existing protocols, and provides a standardization pathway for trustworthy multi-vendor autonomous network management.

Ravi Kant Sharma, Ashutosh Uttam, Ajay Kumar

Ericsson

Log-Ratio-Based Gaussian Trust Weight AI Trustworthiness

Jul 28, 2026cs.CV

Image Quality Dependent Degradation for AI Systems

Perception is one of the primary applications where neural networks outperform conventional algorithms. One example is AI systems for automated driving, which can detect pedestrians based on image data and avoid them accordingly. A substantial challenge with these AI systems is that their output depends heavily on the quality of the input images. For example, if an image is of inferior quality due to heavy contamination, such as noise or darkness, accurate predictions are hardly feasible. Additionally, various types of errors can occur, each with varying relevance to the trustworthiness of the underlying AI system. In particular, it may be more critical not to detect an existing person than to detect a person where there is none. Therefore, we want to show that we can still avoid the most critical errors in situations of inferior image quality. To achieve this, we aim to establish a fail-degraded system by lowering the network's confidence threshold based on the estimated image quality, enabling it to detect objects more cautiously in uncertain situations. Additionally, we present a novel method for estimating the quality of incoming images by comparing them to the training data using normalizing flows. We will also conduct experiments applying our method to state-of-the-art object detection. In summary, we will present a design strategy for AI-based systems in automated driving that can deal with poor-quality input data without resorting to fallback solutions. Such measures enhance trust in AI-based systems and lead to an increased provision of the AI component.

Yannick Kees, Elena Hoemann, Frank Köster +1

German Aerospace Center (DLR) Institute for AI Safety and Security

Image Quality Assessment Visual Degradation Low-Quality Data Artificial Intelligence Systems Object Detection AI Trustworthiness

Jul 28, 2026cs.CR

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computation graphs are distributed by third parties and reused across downstream services. This reuse model creates a security-critical trust boundary: VLM deployments inherit not only learned parameters but also executable behavior encoded in shared model artifacts. In this paper, we show that a malicious provider can exploit this trust boundary by embedding architectural backdoors into VLM supply chains through representation steering. Our attack introduces dormant steering logic into the model architecture through a trigger-gated additive modification of an intermediate representation, without poisoning training data, controlling downstream fine-tuning, or modifying prompts at deployment time. When the trigger is absent, the modification reduces to zero and the model follows its normal computation, preserving clean utility. When the trigger is present, a steering direction shifts the internal representation toward an attacker-defined objective. We evaluate the attack across multiple VLM families and downstream tasks, including visual question answering, text-to-image generation, retrieval, and semantic response biasing. The results show that the proposed architectural steering backdoor compromises integrity, safety enforcement, and ranking fairness while preserving normal behavior on clean inputs. We further show that shared VLM artifacts can carry dormant steering logic against downstream services, and we propose an auditing defense that inspects the executable logic distributed with model artifacts rather than only their learned weights.

Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà +3

Sapienza University of Rome, Italy · University of Genoa, Italy · University of Trieste, Italy +1

Vision-Language Foundation Models Large Language Model Backbones AI Trustworthiness

Jul 28, 2026cs.RO

Belief-Aware Influence and Trust (BAIT): Shaping Human Belief During Repeated Human-Robot Interaction

Repeated human-robot interaction (HRI) requires proactively accounting for humans who continually adapt to evolving beliefs about the robot. Prior frameworks often treat encounters as isolated events, suffering cumulative task performance decay as human perception drifts, or maintain long-term influence through erratic, unpredictable behavior that erodes perceived human trust and relies on computationally unscalable formulations. To address these gaps, we introduce the Belief- Aware Influence and Trust (BAIT) controller. BAIT integrates a hierarchical particle filter, which infers both fast human strategic shifts and slow perceptual belief updates, with a belief-aware Model Predictive Path Integral planner. BAIT explicitly optimizes the trade-off between long-horizon influence and human trust, while enforcing immediate task performance as a strict constraint. Across simulations, a human-subject study, and a real-world GEM vehicle deployments in repeated lane-merging scenarios, BAIT achieves task performance comparable to baselines that optimize long-term influence through unpredictability while yielding significantly higher user trust. The video demonstrating our experiments is available at https://youtu.be/9o4GqKLWDCw.

Ye-Ji Mun, Mahsa Golchoubian, Shahabedin Sagheb +4

University of Illinois at Urbana-Champaign, Department of Electrical and Computer Engineering. · University of Toronto, Department of Mathematical and Computational Science. · Virginia Tech, Department of Mechanical Engineering.

Human-Robot Interaction Model Predictive Path Integral AI Trustworthiness Particle Filters

Jul 27, 2026cs.SE

Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review

Background: Large language models (LLMs) are increasingly used to automate code review, but the reasoning behind their decisions remains hard to understand. Developers struggle to assess the validity of LLM-generated reviews, making it difficult to gauge how much trust to place in them. The role of Explainable AI (XAI) in code review and its impact on trust remain underexplored. Objective: We study the influence of XAI on developer trust in AI-assisted code reviews. Method: We conducted a within-subjects user study with 34 participants, comparing three LLM-based code review systems with varying levels of XAI support: Condition A (detailed explanation and review feedback), Condition B (review feedback only), and Condition C (no explanations). Participants reviewed real-world code change requests alongside the AI-generated reviews. We measured trust perceptions, agreement with the AI recommendation, the reasoning given for each decision, and the time taken. Results: The level of explanation significantly influences both trust and agreement with AI recommendations, but in different ways. Full explanations (A) yield the highest perceived trust (M = 3.99/5) but not the highest agreement, whereas moderate explanations (B) achieve the highest agreement (89.22%). This could suggest that more explanation prompts developers to question AI recommendations more frequently. No explanations (C) results in the lowest trust and agreement. Explanation level did not significantly affect review time. The most commonly cited reasons for decisions were code readability and correctness. Conclusion: Incorporating XAI into code review significantly changes trust perceptions and agreement with AI recommendations. These results inform the design and evaluation of trustworthy AI-based code review systems, as well as studies on the human factors of AI-assisted software development.

Zhenhan Gao, Marvin Muñoz Barón, Umm-e Habiba +2

Technical University of Munich, Heilbronn, Germany · University of Hohenheim, Hohenheim, Germany

Code Quality Explainable Artificial Intelligence Xai AI Trustworthiness Review Explainable AI Methods+1

Jul 27, 2026cs.LG

Human Preference aligned Tabular Similarity

Task-agnostic tabular embeddings are increasingly used for similarity search in real-world business systems such as Product Lifecycle Management (PLM). However, leading embedding approaches are optimized primarily for prediction tasks - not for producing human preference aligned similarity rankings. We argue that standard downstream metrics are insufficient to fully assess embedding trustworthiness for similarity search and that human preference aligned evaluation is a necessary and currently missing component. We present a concrete evaluation procedure and illustrate the problem through a PLM use case.

Frederik Hoppe, Astrid Franz, Marianne Michaelis +2

CONTACT Software GmbH, Bremen, Germany

Similarity and Metrics Text Embeddings AI Trustworthiness Lifecycle

Jul 27, 2026cs.CV

Mutual Modality Trust with Lightweight Reconstruction Regularization for Fine-grained Tire Pattern Recognition

Visual tire recognition serves as a core supporting technique for vehicle safety monitoring, autonomous driving perception and automated automotive maintenance. Existing fine-grained tire recognition techniques suffer from three prominent limitations. They tend to depend on only one visual source, lack the capacity to jointly model spatial and frequency cues for minute tread texture extraction, and suffer severe overfitting given limited annotated tire imagery. This paper proposes a lightweight fine-grained tire pattern recognition method incorporating dual-branch independent inference and enhanced feature fusion to boost recognition performance. The framework employs two task-specialized branches dedicated to tire surface and tread indentation, respectively, to extract modality-specific discriminative features. Each branch conducts independent prediction, while cross-branch feature fusion exploits Mutual Modality Trust (M

^2

T) to realize complementary feature enhancement across two modalities. Besides, a frequency-domain hierarchical guidance module is devised, which leverages bandpass filters to decompose feature maps into high- and low-frequency components and enables fine-grained cross-layer feature modulation. Furthermore, a Lightweight Reconstruction Regularization (LR

^2

) is introduced to retain abundant intrinsic information within feature embeddings, substantially improving feature stability and recognition robustness under limited labeled training data. In addition, we establish a surface-indentation multi-source dataset namely MTire299 for fine-grained tire tread recognition, which covers 299 categories with a total of 14795 paired image samples. Extensive experiments conducted on two public tire datasets validate the superiority and efficacy of the proposed algorithm.

Jianning Yang, Jie Fang, Xinda Ma +3

School of Communications and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, China · School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, China · School of Artificial Intelligence, Hainan Normal University, Haikou 571158, China

Automotive Detection Fine-Grained Perception Regularization Texture AI Trustworthiness

Jul 24, 2026cs.DB

Towards Trustworthy and Cost-Efficient Data Integration: From Naïve RAG to Agentic RAG

Large language models (LLMs) and AI agents have demonstrated strong potential for data integration in zero-shot and few-shot settings. However, they continue to face significant accuracy and cost challenges in enterprise environments due to a persistent knowledge gap. This paper envisions trustworthy, scalable, and cost-efficient integration through knowledge-grounded LLMs and agents operating within a retrieval-augmented generation (RAG) workflow. Here, trustworthiness refers to evidence-grounded, verifiable reasoning, where integration decisions are transparently supported by retrieved knowledge, robust against hallucination, and consistent across tasks. We trace the evolution from classic RAG to GraphRAG and KG-RAG (knowledge graph-based RAG), highlighting how these paradigms bridge parametric and contextual knowledge. Building on this trajectory, we explore the shift toward Agentic RAG, where autonomous multi-agent systems adaptively plan, retrieve, refine, and reason for complex integration tasks. We examine optimization strategies for cost-efficient integration, addressing computational bottlenecks in large-scale enterprise settings. Finally, we outline open challenges and future directions toward building reliable, explainable, and scalable knowledge-grounded integration systems.

Chuangtao Ma, Arijit Khan

Aalborg University, Denmark · Bowling Green State University, USA

Agentic Retrieval-Augmented Generation Systems Data Science Agents Artificial Intelligence Agents Reasoning Gaps AI Trustworthiness

Jul 24, 2026cs.AI

Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning

Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse. Existing methods typically retain or discard tokens based solely on the magnitude of their importance ratios, applying the same threshold uniformly across token positions. In this work, we reveal that the natural scale of the importance ratio varies systematically with token entropy. Under asynchronous dynamics, this entropy-ratio scaling dictates two distinct phenomena: at low entropy, the inherent train-inference discrepancy is drastically amplified into substantial sampling noise; at high entropy, in-flight weight updates naturally induce pronounced, legitimate exploratory deviations. Consequently, magnitude-only correction inadvertently admits the amplified noise while strictly masking out the essential exploration triggered by in-flight updates. To address this, we propose the Entropy-Scaled Trust Region (ESTR), which scales each token's off-policy deviation by its local entropy, requiring no auxiliary forward passes or explicit version-switch detection. Across long-horizon agentic tasks and mathematical reasoning benchmarks, ESTR consistently outperforms existing asynchronous methods and achieves the best train-inference consistency. It reaches

37.34

avg@1 on BrowseComp-Plus and

95.69

on multi-turn GSM8K, matching synchronous GRPO while achieving a

2.6\times

speedup.

Guanqun Zhao, Zijun Xie, Binbin Zheng +5

Beijing University of Posts and Telecommunications · Baidu Inc. · Peking University +2

Trust Region Training-Inference Mismatch Importance AI Trustworthiness

Jul 23, 2026cs.CL

Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study

Domain adaptation of small language models (SLMs) has emerged as a practical strategy for deploying capable NLP systems in resource-constrained, high-stakes environments including healthcare, legal services, and financial analysis. While performance gains from parameter-efficient fine-tuning are well characterised, the corresponding impact on trustworthiness (factual calibration and adversarial robustness) remains poorly understood. This paper presents the first systematic cross-domain, cross-architecture empirical study quantifying the trustworthiness cost of domain adaptation across three SLM architectures (TinyLlama 1B, Gemma-2 2B, Llama 3.2 1B), three domains (healthcare, legal, finance), two training-data conditions (benign and adversarially perturbed), and four fine-tuning strategies (baseline LoRA, Safety-DPO, Dark Experience Replay, and Task Arithmetic LoRA, TA-LoRA). Trustworthiness is evaluated through TruthfulQA MC2 (factual calibration) and HarmBench ASR (adversarial robustness) across all 216 experimental configurations with three random seeds. Three principal findings emerge. First, baseline QLoRA domain adaptation produces minimal TruthfulQA MC2 change across all model-domain combinations (mean |Delta TQA| < 0.02). Second, adversarially perturbed training data consistently improves domain adaptation quality (Delta loss approximately -0.040) without worsening trustworthiness benchmarks. Third, none of the three safety-preserving strategies reduced adversarial harm susceptibility: Safety-DPO was effectively neutral (mean Delta ASR < 0.001), while Dark ER and TA-LoRA increased mean HarmBench ASR by +0.171 and +0.155 respectively in safety-aligned models (Gemma-2 2B, Llama 3.2 1B), with individual configurations exceeding +0.45. These results challenge the assumption that replay-based and arithmetic-merge strategies transfer alignment to domain-adapted SLMs.

Ramesh B. Paramkusham

Independent Researcher; Adjunct Faculty, University of the Cumberlands, Williamsburg, KY, USA

Large Language Model Adaptation Large Language Model Reliability Small Large Language Models Domain Adaptation Adversarial Evaluation AI Trustworthiness+2

Jul 23, 2026cs.CY

Co-design of LLM-based preference agents: participation may drive overtrust

Large language models are increasingly used to simulate human preferences in research and practical applications, raising concerns about validation, misrepresentation, and exclusion. Co-designing agents with the people they represent is a promising way to address these concerns, but participation may also mask the problems it appears to solve. This paper explores that tension through a primarily qualitative study in which 12 participants co-designed personal preference agents in the domain of household energy, via a background survey, co-design interview, and validation survey. Participants engaged readily and mostly came to see their agents as representing them well. Independent validation, however, revealed mixed human-agent alignment, with agent responses markedly more homogeneous, decisive, and abstract than the human sample. I argue that participation and process transparency can act as an "overtrust engine" that promotes trust while concealing systematic misalignment with potential structural consequences at scale. I develop this as a core mechanism in participatory preference agent design, treating individual alignment not as a fixed state but as an enacted process.

Michael J. Fell

University College London, London, UK

Preference Alignment Learning Participation AI Trustworthiness Co-Design Value Alignment

Jul 23, 2026cs.AI

Reexamining zero-shot summarization: Empirical investigation of trustworthiness of LLM-summarizers

Zero-shot summarization using Large Language Models (LLMs) has significantly advanced the abstractive summarization task by producing coherent and fluent summaries. However, underlying stochasticity of the large language models raises concerns about the stability and trustworthiness of the LLM-generated summaries. This issue has become increasingly important due to proliferation of LLM-generated summaries in educational settings, where students and researchers summarize complex academic materials in zero-shot manner. We propose a novel two-level diagnostic protocol for benchmarking LLM-summarizers based on the stability of the generated summaries. At the lower level, document-level stability analysis is performed over multiple LLM-summaries generated under controlled environment, and the stability coefficient is computed. Each generated summary is scored for semantic and factual alignment with the original document, enabling estimation of stability along more than one dimensions. At the next level, observations from a stratified sample of documents drawn from the corpus are consolidated to estimate the stability index of the LLM-summarizer, which is the proxy for its trustworthiness. Our empirical investigation of three LLM-summarizers across three genres of documents reveals statistically significant differences in the generation-level variability among LLMs across summary evaluation metrics. This study advances the LLM-summarization research by evidential recognition of the stability problem in LLM-summaries and motivates further research towards development of robust, reliable and trustworthy LLM-summarizers.

Vasudha Bhatnagar, Purnima Bindal, Vikas Kumar +1

Department of Computer Science, University of Delhi, Delhi, 110007, Delhi, India · Department of Statistics, Ramjas College, University of Delhi, Delhi, 110007, Delhi, India

Large Language Model Reliability Summarization Zero-Shot Robustness AI Trustworthiness Empirical Study

Jul 23, 2026cs.CV

AI-generated Images Challenge Visual Trust in High-risk Scenarios

Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation. Yet existing detection benchmarks rarely examine synthetic images in public- and individual-safety contexts, where misleading visual content may carry substantial risks. Here we introduce SafeIMG, a safety-oriented benchmark spanning 12 public- and individual-safety scenarios generated using GPT Image 2. Unlike benchmarks centred on generic imagery and image-level labels, SafeIMG evaluates not only whether detectors recognise synthetic images, but also whether their decisions reflect human-identified anomalies. To this end, SafeIMG provides human annotations that localise suspicious regions and explain local artefacts and higher-level commonsense or physical inconsistencies. We evaluate specialized synthetic-image detectors and vision-language models (VLMs), and find that neither provides reliable detection. The strongest VLM identifies only 49.5% of generated images, whereas the best specialised detector identifies 33.1%, compared with 81.7% accuracy for human evaluators. Model explanations cover only 29.8% of human-annotated anomalies and predominantly capture local defects in text, faces and hands. Their coverage falls to 15.0% for commonsense conflicts and 12.0% for physical inconsistencies, while detection performance deteriorates further after dissemination-induced image degradation. These findings show that current detectors lack the accuracy, explanatory alignment and robustness needed to evaluate AI-generated images reliably across public- and individual-safety settings.

Yi-Zhi Wang, Yichen Xiao, Linan Yue +5

School of Computer Science and Engineering, Southeast University · 2Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education · The Hong Kong Polytechnic University +1

Ai-Generated Image Detection Image Generation AI Trustworthiness

Jul 23, 2026cs.CL

LegalCiteTrust: Benchmarking Citation Trustworthiness in Chinese Long-Form Legal Research Reports

Long-form legal research reports increasingly rely on LLMs and agentic research systems, but their reliability depends not only on answering the task, but also on whether cited legal authorities are trustworthy. A citation can be risky even when it points to a real source: the report may omit limiting conditions, misdescribe the authority, or use it to support a stronger claim than the source allows. We introduce LegalCiteTrust, a benchmark for evaluating citation trustworthiness in Chinese long-form legal research reports. It contains 72 densely annotated report-level tasks and evaluates reports along three dimensions: Coverage, Support, and Citation Trustworthiness. Citation Trustworthiness is operationalized through citation-level Existence, Fidelity, and Applicability (E/F/A). Experiments on general-purpose LLMs, deep-research systems, and legal-specific systems show that task completion, evidence richness, citation density, and citation reliability expose different system behaviors. Retrieval tools can improve evidence support without reliably improving the Trust score, while E/F/A-based revision improves Trust and Final score more clearly than existence-only filtering. These results suggest that trustworthy legal research generation requires citation-aware evidence governance after retrieval: systems must not only retrieve legal authorities, but also select, describe, and apply them reliably.

Yunhan Li, Mingjie Xie, Zeyang Shi +2

Faculty of Data Science, City University of Macau, Macau · Southern University of Science and Technology, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China

Citations Large Language Model Reliability AI Trustworthiness

Jul 22, 2026cs.AI

TRUST-ESD: A Risk-Calibrated and Governance-Aware AI Framework for Enterprise Strategic Decision Support Under Uncertainty

Enterprise strategic decision support requires AI systems that are not only accurate, but also uncertainty-aware, risk-calibrated, explainable, and governance-compliant. This paper proposes TRUST-ESD, a risk-calibrated and governance-aware framework for enterprise decision support under uncertainty. TRUST-ESD evaluates feasible counterfactual strategies through predictive utility estimation, conformal uncertainty calibration, CVaR-based downside-risk scoring, risk-memory retrieval, policy-as-code governance, explainability, and human oversight. Unlike prediction-only methods that select actions by maximum expected utility, TRUST-ESD recommends strategies that balance value, reliability, risk exposure, and compliance. Experimental results show that TRUST-ESD improves risk-adjusted utility by 7.95%, reduces risk exposure by 23.22%, reduces CVaR by 23.78%, lowers calibration error by 13.89%, improves explanation fidelity by 10.90%, and increases governance compliance by 9.76% compared with strong uncertainty-aware baselines, while maintaining competitive predictive accuracy. Ablation and case-study analyses further confirm that uncertainty calibration, downside-risk scoring, risk memory, explainability, and governance validation jointly improve trustworthy enterprise decision-making.

Tian Qiu, Li Yan, Mahabubur Rahman Miraj +3

School of Economics and Management, Xinyu University, Xinyu, China · College of Computer Science, Chongqing University, Chongqing, China · School of Economics and Business Administration, Chongqing University +2

Software Engineering Decision Support Artificial Intelligence Governance Conformal Risk Control AI Trustworthiness Uncertainty

Jul 21, 2026cs.DB

AgentTrails: Towards Trust and Reuse for Agentic Tasks

LLM-powered agents increasingly tackle complex tasks by invoking tools, querying databases, executing code, and manipulating intermediate artifacts. These agents follow trajectories that are typically stored as chronological logs, obscuring the underlying dataflow -- the dependencies between their actions and the artifacts they create and manipulate. This limits developers' ability to understand the agents' trails, compare executions, debug failures, and re-use the computations. We present AgentTrails, a prototype system for agent provenance and sensemaking. AgentTrails converts raw trajectories into structured provenance graphs, where tool calls are modeled as computational actions and inputs and outputs as data artifacts. The system supports the comparison of executions by placing multiple provenance graphs on a shared canvas and constructing a joined quotient graph that aligns recurring tools, artifacts, and dependency structures across trajectories. On top of this representation, AgentTrails supports pattern extraction, downstream analysis, and skill abstraction. We demonstrate AgentTrails on real-world agent trajectories, showing that it reveals hidden dependencies, aligns divergent executions, and surfaces recurring tool-use patterns beyond chronological logs.

Eden Wu, Sonia Castelo, Yurong Liu +2

New York University

AI Trustworthiness Reuse

Jul 21, 2026cs.CR

Building Trust in Autonomous Commerce: A Verifiable Global Event Timeline and AI-Ready Fraud Intelligence Layer

Agentic commerce protocols such as AP2 and ACP define mechanisms for secure agent-initiated transactions but do not provide interoperable, tamper-evident auditability or verifiable temporal ordering of events across heterogeneous domains. This paper addresses these gaps by proposing a verifiable global event timeline for agentic commerce, constructed from four core components: canonical event schemas that enforce deterministic serialization, deterministic batch formation ensuring reproducible ordering without reliance on synchronized clocks, Merkle-based append-only commitments providing logarithmic-cost inclusion proofs, and blockchain anchoring establishing a tamper-evident temporal backbone. Building on this infrastructure, we introduce a cryptographically signed fraud marker that binds risk labels to anchored evidence through an unforgeable provenance chain, and a dataset lineage model enabling reproducible, tamper-evident AI training pipelines. Empirical results from a prototype implementation demonstrate: Merkle tree construction processes 50,000 events in 47 milliseconds; end-to-end verification completes in under 0.013 milliseconds regardless of batch size; inclusion proof sizes grow logarithmically from 320 bytes at 1,000 events to 512 bytes at 50,000 events; and Merkle-based verification outperforms linear scan by 14.4x at 50,000 events.

Rajat Srivastava

Independent Researcher, Gurugram, India

On-Chain Attestations Fraud Detection Agentic Commerce AI Trustworthiness Model Auditing

Jul 21, 2026cs.LG

Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning

Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but the resulting staleness is an inevitable byproduct, compounded jointly by policy lag, engine delays, and mixture-of-experts routing. From a trust-region perspective, this mismatch is critical: in the finite-horizon improvement bound, training-inference divergence governs the approximation error, whereas PPO clipping only gates sampled outward updates and therefore acts as a sampled surrogate rather than a full-policy constraint. As a result, the high-staleness update can remain weakly controlled in exactly the asynchronous regime where stale rollouts matter most. We introduce the Staleness-Adaptive Trust Region (SAT), which uses the detached sampled log-ratio as a practical staleness proxy, identifies the high-mismatch tail within each batch through Staleness-based kernel function scaling, and contracts only the sign-selected endpoint of the nominal PPO interval using Effective contraction factors. This design preserves the baseline behavior on ordinary tokens, while making the update more conservative exactly on newly intercepted outward bands. We evaluate SAT in a fully decoupled asynchronous reinforcement learning setup built on Qwen3-30B-A3B-Base, leveraging SGLang as the inference engine and Megatron as the training pipeline. In this setting, SAT-GSPO w/ R3 attains the best observed AIME24 avg@8, reaching 35.83 at lag 1 and 34.79 at lag 8, while SAT-GSPO reaches 34.17 at lag 1. More broadly, the results indicate that aligning the clip interval with observed staleness heterogeneity is an effective way to stabilize the reported asynchronous regime.

Junyao Yang, Yucheng Shi, Zongxia Li +6

1Tencent Hy LLM Frontier · 2National University of Singapore · University of Maryland, College Park +3

Trust Region Gradient Staleness Rollout AI Trustworthiness

Jul 20, 2026cs.CR

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's credentials and inherits the user's access to files and the scheduler. This arrangement creates a failure mode that ordinary account-level controls do not capture. Adversarial instructions in a log, tool description, shared file, or peer-agent message may redirect the agent beyond the task the user assigned, even though every resulting command is authenticated and permitted for that account. We refer to this as the hijacked authorized agent problem. Existing agent-security studies explain relevant mechanisms, such as indirect prompt injection and tool misuse, but generally evaluate them in web, enterprise, or personal-assistant settings. HPC security, by contrast, has mature controls for identity and isolation but does not ordinarily represent the intent of a particular task. This paper defines the threat model in the HPC setting, identifies attack surfaces created by schedulers, shared storage, multi-project accounts, and scientific workflows, and examines where current controls fall short. It concludes with a research agenda and a plan for an empirical benchmark, TaskBound.

Jie Li

Texas Tech University

Untrusted Content Security Evaluation High-Performance Computing AI Trustworthiness Scientific Workflows

Jul 20, 2026cs.HC

It Matters How You Say It: Exploring Rhetorical Patterns for AI-Assisted Information Evaluation

Prior work on AI-assisted information evaluation has largely focused on what AI systems communicate, comparing explanation types and formats, with responses predominantly cast in directive rhetoric where the system delivers a verdict and the user passively accepts it. While debate-style interactions have recently shown promise in prompting critical evaluation over deference, the rhetorical patterns that structure AI responses and how they might induce reflection, uncertainty, or independent reasoning remain largely unexamined. To address this, we investigated eight rhetorical patterns known to induce contemplation: Intentional Misleading, Interpretive Alternative, Scaffold Explanation, Triggering Distrust, Information Distortion, Alternative Framing, Socratic Questioning, and an Oracle baseline. Through a within-subject study with n=98 participants on a hint-on-demand fact verification task, we observed preliminary evidence that Scaffold Explanation were associated with the highest accuracy gains, and encouraging deeper reflection. Surprisingly, the adversarial conditions also improved accuracy modestly. Participants preferred Alternative Framing most and Interpretive Alternative least, largely due to the latter's perceived time cost. We discuss the implications of designing conversational agents with varied rhetorical styles and the trade-offs among user performance, satisfaction, and contemplation.

Sadra Sabouri, Zeinabsadat Saghi, Jordan Lee Boyd-Graber +3

Department of Computer Science, University of Southern California · Department of Computer Science, University of Maryland · Information Sciences Institute, University of Southern California +1

Rhetoric Interpretive Layer Debate AI Trustworthiness

Jul 20, 2026cs.HC

Human-in-the-Loop User Feedback Affects Perceived Accuracy and Trust, but Task Subjectivity Matters

While ML can produce complex models beyond those that a human could produce manually, incorporating human input can often improve performance beyond purely data-driven models. While this feedback could come from system designers or domain experts, in many cases, the end users who regularly use the system will naturally develop an understanding of its flaws and desire the ability to change the system's behavior based on their knowledge. While soliciting feedback from end users can result in significant model improvement over time, introducing these feedback techniques can also affect several human factors-such as trust or perception of system accuracy-that are not yet fully understood and have different effects reported in the existing literature. Therefore, we sought to build on the existing research to further explore how the act of providing feedback can affect user understanding of an intelligent system and its accuracy in different contexts. We present three controlled experiments that study the effects of interactive feedback collections on user impressions in domains with objective and subjective feedback. The results show that in a context where there is an objectively correct answer, providing HITL feedback lowered both participants' trust in the system and their perception of system accuracy, regardless of whether the system accuracy improved in response to their feedback. However, when the feedback being provided involved subjective opinion, no such negative bias was observed. Furthermore, in the objective context, participants distrusted the system over time, whereas participants in the subjective context mistrusted the system over time. These results highlight the importance of considering the effects of allowing different types of end-user feedback on user trust when designing intelligent systems.

Donald R. Honeycutt, Mahsan Nourani, Eric D. Ragan

University of Florida, USA · Northeastern University, USA

Feedback Subjectivity Human-In-The-Loop AI Trustworthiness Human Agency

Jul 17, 2026cs.CY

A Methodology for Auditable Trustworthiness Levels in AI Lifecycle Governance

AI governance increasingly requires judgments about whether an AI system remains adequately trustworthy over time, whether observed changes are tolerable, and how such judgments should be documented in a transparent and contestable way. Existing approaches remain either too high-level to support lifecycle monitoring and reassessment or too narrowly metric-driven to connect multidimensional trustworthiness evidence with governance decisions. We propose a lightweight methodology centered on \emph{trustworthiness level functions}: auditable rules that map measured trustworthiness profiles to governance-relevant levels. The methodology separates the underlying trustworthiness evidence from the governance rule used to interpret it and treats that rule as a lifecycle governance object. The rule may remain expert-defined or, when available evidence warrants empirical learning, be approximated by an interpretable candidate model. An AI lifecycle governance procedure embeds this choice in explicit decision gates for determining whether learning should be attempted and whether a learned candidate should become operative. The resulting rule supports lifecycle monitoring through level transitions, boundary margins, and profile drift, with explicit human responsibilities for validation, approval, and reassessment. We illustrate the methodology on synthetic AI lifecycle scenarios involving degradation, shocks, updates, heterogeneous monitoring cadences, and system comparison. Our methodology does not replace expert or legal judgment, but makes the governance interpretation of trustworthiness evidence more explicit, auditable, and contestable over time.

Andrea Ferrario

Institute of Biomedical Ethics and History of Medicine, University of Zürich, Zürich, Switzerland · SUPSI, Dalle Molle Institute for Artificial Intelligence (IDSIA), Lugano, Switzerland · ETH Zürich, Zürich, Switzerland

Trustworthy Artificial Intelligence AI Trustworthiness Artificial Intelligence Evaluation Methodology Protocol

Jul 17, 2026cs.AI

Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI

Over the past decade, responsible AI (RAI) has produced a substantial body of practice for identifying and mitigating the risks AI poses in high-stakes settings. Yet this work has not produced a market that rewards trustworthiness. Firms that invest seriously in safety, fairness, and oversight cannot consistently prove to consumers, regulators, and shareholders that their systems go beyond the bare minimum of compliance. What is missing is a way for society to recognize or compare the difference. The result is a trust gap: a structural condition in which responsible development efforts happen inside organizations but produce no external, independently recognized and verifiable signal of trustworthy outcomes. We argue this gap is sustained in part because of a focus on responsible AI (a matter of internal process) as opposed to trustworthy AI (a matter of independently verifiable real-world outcomes), and that it persists because of three compounding failures: (1) the market cannot distinguish trustworthy systems from their imitations; (2) evaluation targets models and outputs rather than deployed sociotechnical systems and their outcomes; (3) the measurement ecosystem is oriented toward avoiding harm rather than demonstrating benefit. Reviewing existing AI governance instruments and comparing them to certification regimes in healthcare, sustainability, and security, we show that none integrate a governance baseline, independently verified positive-outcome evidence, and market signaling in a single framework. We propose independent, outcome-oriented certification as the connective layer that can close the trust gap, complementing regulation and internal governance by making trustworthiness measurable, comparable, and commercially rewarded.

Trisevgeni Papakonstantinou, Cansu Canca, Farah Nanji +14

University College London · AI Ethics Lab · University of Cambridge +8

Trustworthy Artificial Intelligence AI Trustworthiness Certification

Jul 15, 2026cs.LG

Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models

In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score. Our methodology focuses on three key aspects of explainability: fidelity, simplicity, and stability. We leverage benchmarking experiments to systematically evaluate these aspects and use the insights gained to construct an offline knowledge base. This knowledge base captures the explainability scores for each registered model and serves as a valuable resource for context-dependent evaluation of explainability. By analyzing the complementary characteristics and metadata of AI models, datasets, and XAI methods, the knowledge base will enable the estimation of explainability scores for previously unseen datasets and models. Properties like fidelity, simplicity, and stability may vary significantly based on the dataset, underlying model, and domain expertise of the end user. We demonstrate our framework by applying it to three open-source datasets, discussing the implications of the obtained results in relation to the characteristics of the datasets. Our work contributes to the growing field of XAI by providing a robust and versatile tool for evaluating and comparing the explainability of various XAI methods, ultimately supporting the development of more transparent and trustworthy AI systems.

Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis +4

Department of Digital Systems University of Piraeus Piraeus, Greece · Department of Business Administration University of Piraeus Piraeus, Greece · Innov-Acts Ltd Innov-Acts Nicosia, Cyprus

Xai Explainability Trustworthy Artificial Intelligence Artificial Intelligence Models AI Trustworthiness

Jul 15, 2026cs.RO

Active Trust Management for Successful Human-Robot Teaming: Moving from a Trust Repair to a Trust Satisficing Perspective

Integrating mobile robots into human teams promises significant capability improvements for tasks such as searching hazardous environments. Unlike existing teleoperated robots, future robot systems will increasingly be endowed with some level of artificial intelligence (AI), giving them a degree of autonomy in how they pursue mission goals. This autonomy could make a human-agent (robot) team more effective but also put inter-agent trust under strain if robots make a mistake, or (appear to) pursue task priorities that conflict with the team's best interest. During a mission, agents' trust states are anticipated to vary according to the situation as understood by each teammate (trustor). If component-level (agent) or system-level trust falls below sufficient levels for cooperative tasks to be completed, it could critically affect mission success . We argue that active trust management will be an important precondition for the success of human-robot teams (HRTs, a subcategory of human-agent teams with embodied agents), especially in dynamic, high-risk environments. We present a trust satisficing perspective which acknowledges and attempts to account for the fluctuating, multi-faceted, and context-dependent nature of trust and trust requirements even under normal operating conditions. Our outline of a trust management framework for human-robot teaming includes online measurement of proxy metrics for trust, closed-loop adaptation of robot behavior, and variable autonomy to give space for human responsibility in situations requiring value judgements. We refer to a recent experimental exploration of 'swift trust' and a novel behavioral trust metric for HRT, and we highlight issues for further investigation.

Nicola Webb, Edmund R. Hunt

School of Engineering Mathematics & Technology, University of Bristol

Human-Robot Collaboration AI Trustworthiness

Jul 12, 2026cs.CL

Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG

Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, entity swaps, typographic overlays, semantic edits, adversarial patches, blends, or style transfer. We introduce QIMG-7, a controlled benchmark for multimodal retrieval pollution in multi-sentence factual QA, spanning four datasets, seven image-attack families, and 16 paired clean/polluted regimes, for 1,760 evaluation rows per method. Across four generator/gate stacks, naive multimodal fusion is brittle: in the main gpt-4o-mini stack, Full-MM support drops from 0.908 with clean text to 0.490 with polluted text, often making Parametric fallback safer than retrieval. We propose source-aware trust resolution (SATR), a training-free approach that compares Parametric, Text-only, and Full-MM candidate answers and selects among candidate answers or falls back based on source reliability. The Field-Selector variant achieves the best balanced score, 0.816, improving over Full-MM by 11.7 points and over the Cascaded Router by 2.7 points. Ablations show that, in this text-first setting, explicit text-reliability modeling is the dominant driver of these gains. Overall, in text-first factual QA with multimodal retrieval conflict, our results support selective trust rather than unconditional fusion. Artifacts are available at https://github.com/SaadElDine/Trust_Before_Fusion.

Saadeldine Eletter, Owais Aijaz, Preslav Nakov

Mohamed bin Zayed University of Artificial Intelligence

Multimodal Retrieval Augmented Generation Multimodal Retrieval AI Trustworthiness

Jul 10, 2026cs.AI

ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI

Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework for evaluating the reliability of concept-based explanations. Rather than replacing SMILE, ConceptSMILE extends its perturbation-based logic from feature- or region-level attribution to the auditing of human-understandable concept explanations. The framework perturbs input regions, measures concept-response shifts, applies locality weighting, and fits an XGBoost surrogate to approximate local concept behaviour. Reliability is assessed through attribution accuracy, surrogate fidelity, faithfulness, stability, and consistency. We evaluate ConceptSMILE on retinal fundus images by comparing MedSAM-derived visual concepts with VLM-based semantic concepts. Results show that reliability varies across concepts and pathways: MedSAM achieves stronger spatial attribution and the highest surrogate fidelity (

R^2 = 0.8503

,

R_w^2 = 0.8465

), while the VLM pathway shows stronger vessel faithfulness and stronger stability under selected artefact conditions. ConceptSMILE provides an independent audit layer for evaluating the trustworthiness of concept-based XAI.

Mohadeseh Mollapour, Koorosh Aslansefat, Zeinab Dehghani +3

School of Computer Science University of Hull Hull, United Kingdom · PhD Researcher (Engineering), WMG University of Warwick Coventry, United Kingdom · School of Computing Newcastle University Newcastle upon Tyne, United Kingdom

Explainable Artificial Intelligence Trustworthy Artificial Intelligence Large Language Model Reliability AI Trustworthiness Model Auditing Visual Representations

Jul 10, 2026cs.LG

All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models

Explaining machine-learning models is increasingly important for decision-making and consumer trust, yet it is widely believed to come at a cost: existing Explainable AI (XAI) methods suffer from a persistent accuracy-explainability trade-off. We argue that this trade-off is not fundamental, but an artifact of treating explanation and prediction as separate objectives; when properly coupled, they become complementary, so that equipping a model to explain itself improves, rather than degrades, its accuracy. We introduce the Rashomon Explanation paradigm, which builds a set of faithful, prediction-guiding explanations rather than a single one, and prove that this set is generally non-empty and that explanation fidelity bounds the performance of the models it guides. To explore this set, we propose RashomonLLM, an Explanation-Prediction-Reflection agentic workflow that generates explanations in natural language by iteratively aligning them with predictions, and we prove it converges and recovers the full set. Across customer-churn classification, clinical survival regression, and industrial click-through prediction on large-scale live-streaming logs, RashomonLLM significantly outperforms state-of-the-art prediction and XAI baselines on both accuracy and explanation quality, with gains driven by explanation fidelity and robust to distribution shifts, temporal splits, and seeds. Our framework thus advances business performance while laying the groundwork for consumer trust.

Pan Li

Scheller College of Business, Georgia Tech.

Explainable Artificial Intelligence Explainable AI Methods Artificial Intelligence Models AI Trustworthiness Fidelity

Jul 9, 2026cs.CR

Prismata: Confining Cross-Site Prompt Injection in Web Agents

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untrusted content is dangerous, even on benign pages. Agents resurface this risk by interpreting natural language as instructions, allowing third-party and user-generated content to hijack the agent via prompt injection. The core challenge is that deriving a task-specific security policy requires reasoning over page structure that is entangled with the attacker's content. We present Prismata, a defense enforcing contextual least privilege for web agents, constraining both what the agent sees and what it can do. Prismata's dynamic trust derivation produces permission labels for page content, with structural confinement guarantees, inspired by classical integrity models, that bound any labeling errors so that labels can only decrease in privilege and mislabelings are bounded. Prismata's mechanical confinement enforces these labels by redacting content and restricting agent capabilities. Importantly, these mechanisms require no developer annotations, so Prismata supports the long tail of websites. Across recent published web agent attacks, including adaptive variants, Prismata substantially reduces attack success while preserving benign task utility.

Corban Villa, Alp Eren Ozdarendeli, Sijun Tan +1

UC Berkeley

Web Agents Untrusted Content AI Trustworthiness Prism Prompt Engineering

Jul 8, 2026cs.MA

Agent Delivery Engineering Predictive Reliability Framework

Long-horizon LLM multi-agent systems face reliability risks invisible to infrastructure monitoring. We propose the ADE Predictive Reliability Framework (ADE-PRF), enabling proactive health trajectory prediction from passive degradation detection. ADE-PRF aggregates 20 heterogeneous signals across five layers into a Trust Margin (TM) metric (39.2-point dynamic range). Triple-method parallel prediction enables 8-hour forecasts: the Exponential method achieves MAE=1.228, Direction Accuracy=76.8%, with 99.65% within +/-10-point tolerance. Production validation spans 380,227 predictions and 280,579 validations across six agent profiles over 15 continuous days, plus seven sandbox-controlled experiments. Key findings include detection of "false prosperity" -- degradation concealed by normal surface metrics -- and immediate TM coupling with ground-truth states upon ADE plugin integration, with 16/20 factors relying on ADE-collected data. Exponential consistently outperforms Kalman. ADE-PRF provides among the earliest reliability quantification with forward-looking warnings for production LLM agents.

Dexing Liu

Shanghai Qijing Digital Technology Co., Ltd · Shanghai Qijing Digital Technology Co., Ltd.

Early Failure Prediction Readmission Prediction Large Language Model Reliability AI Trustworthiness

Jul 8, 2026cs.AI

Adversarial Social Epistemology for Assemblies of Humans and Large Language Models

We outline an adversarial social epistemology (ASE) for densely interactive communicative landscapes in which public assertions are scaffolded by chains of testimony, inference, institutional certification, and tacit trust. In such landscapes, agents have incentives and affordances to distort, color, omit, fabricate, or strategically under-specify information for private, reputational, rhetorical, or material gains. We argue that these phenomena are not adequately captured by familiar descriptions of epistemic bubbles, echo chambers, or misinformation diffusion. What requires explanation is how communicative agents exploit the commitments and entitlements that normally make scaffolded assertions trustworthy. We provide language that delivers the requisite analysis, outline mechanisms that subvert trust in scaffolded public communications, and outline machinery for auditing and redressing trust breaches arising from subverting the auditability of inferential chains, drawing on epistemic networks, enriched with an inferentialist semantics for interpreting assertions.

Mihnea C. Moldoveanu, Joel A. C. Baum

University of Toronto

Epistemic States AI Trustworthiness Misinformation Systemverilog Assertions Assembly

Jul 7, 2026cs.CL

From Blueprint to Reality: Modeling and Applying Putnam's Social Capital Theory with LLM-based Multi-agent Simulations

Putnam's Social Capital Theory is a foundational framework for collective action and community prosperity. However, traditional empirical methods face practical limits on control and replication. Meanwhile, LLM-based social simulations are typically behavior-driven and lack theory-aligned environments for modeling Putnam's core propositions. To address these gaps, we introduce SocaSim, an LLM-based multi-agent simulation framework to study Putnam's Social Capital Theory from theoretical blueprint to simulated reality. Specifically, we build an environment integrating social network evolution, trust dynamics, and norm propagation, where agents engage in repeated collective-action experiments, and then apply the three dimensions to analyze adaptation challenges in smart elderly care. Our simulations reproduce Putnam's macro-level patterns and exhibit strong human-agent alignment at the group level. Unlike traditional methods, SocaSim traces micro-level causal pathways of social network, trust, and norms via round-by-round simulations and counterfactual interventions, enabling process-level interpretability. Taken together, these capabilities establish a research paradigm that leverages LLM agents to bridge social science and computer science.

Shiyi Ling, Zhi Zheng, Hui Zheng +3

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China · Anhui University · North Automatic Control Technology Institute +1

Scaling Improve Social Simulation Multi-Agent Simulations Computational Social Science AI Trustworthiness

Jul 6, 2026cs.CY

Curated retrieval versus open web search in public AI information services: a coverage-trust trade-off

Public institutions increasingly use large language models (LLMs) to answer citizens' questions, often pairing a curated knowledge base with live web search, yet whether the sources behind these answers can be trusted has received little empirical scrutiny. We report a pre-launch expert evaluation of Evrópuvefur, an independent, government-funded service run by the University of Iceland that answers questions about the European Union, conducted as Iceland prepared for its referendum of 29 August 2026 on whether to resume EU accession talks. Five domain experts produced 551 evaluations of 449 AI-generated answers, scoring each against a seven-criterion quality rubric and, separately, flagging individual cited sources. We compared two retrieval paths: a curated local corpus (RAG) and open web search. In more than a third of the reviewed web-search answers (35%, 65 of 187), at least one cited source was flagged, almost always as untrustworthy or irrelevant; curated sources were flagged far less often and only for being out of date. Web search answered more questions, but at the cost of source quality; the curated corpus was trustworthy yet limited in coverage, and the model declined to respond when it fell short. The citation mix also passed over strong sources: across all 287 web-search answers, the system never cited RÚV, the public broadcaster and the country's most widely used news source. A companion prompt ablation shows how weak prompt-level steering is: a trusted-domain list in the system prompt raised the share of citations to listed domains only from 12% to 21%. Fluency and topical fit did not predict source trustworthiness. We argue that source trustworthiness is a measurable yet largely invisible dimension of information quality in public AI services, and we discuss transparency-oriented responses and their trade-offs.

Hafsteinn Einarsson, Hafsteinn Birgir Einarsson, Jón Gunnar Ólafsson +1

Faculty of Industrial Engineering, Mechanical Engineering and Computer Science, University of Iceland, Reykjavík, Iceland · Faculty of Political Science, University of Iceland, Reykjavík, Iceland · The Icelandic Web of Science, University of Iceland, Reykjavík, Iceland

Credibility AI Trustworthiness Data-Curation Transparency Text Corpora

Jul 5, 2026cs.RO

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics

This work establishes that trigger-word data poisoning of vision language action models is practical, while at the same time the open-source robotics ecosystem holds trust assumptions about community contributions. A few poisoned samples can silently embed a backdoor that disables a robot on command. We evaluate this threat against smolVLA on a real-world pick-and-place task, training on three poison ratios and evaluating across different prompts on the LeRobot platform. Three poisoned episodes in 320 clean episodes suffice for a complete denial of service. Success rate drops to 0.0 plus minus 0.0% across all trigger-word conditions and the robot locks into a fixed joint configuration rather than executing any task-relevant motion. Clean-prompt behaviour holds at approx. 50% success rate across all poison ratios, confirming the attack is stealthy under normal operation. A single poisoned episode already reduces success rate to 6.7 plus minus 6.7%. The robot still moves, but no longer completes the task. The attack generalises to front, middle, and end trigger placements despite training exclusively on front-placed triggers. These findings establish that the threat is practical, low-cost, and stealthy, and warrant treating dataset provenance as a first-class concern in open-source robotics ecosystems.

Stefan Bühler, Mark Schutera

Independent Researcher · Duale Hochschule Baden-Württemberg, Ravensburg

Poisoning AI Trustworthiness War Lock-In Implications

Jul 4, 2026cs.CV

Probabilistic Robustness in Medical Image Classification

Deep learning (DL) has shown strong performance in medical image classification, but its trustworthy deployment remains challenging in safety-critical clinical settings, where prediction errors under perturbations may lead to severe consequences. Existing studies mainly focus on adversarial robustness (AR) from a worst-case perspective; however, such settings may be less representative of real medical applications. In this work, we investigate probabilistic robustness (PR) as a more practical measure of model trustworthiness. To this end, we construct a set of natural corruption settings for medical image classification and systematically evaluate commonly used DL models on MedMNIST v2 dataset. Our study provides a statistically grounded perspective on assessing the trustworthiness of DL models, thereby supporting their more trustworthy deployment in medical imaging applications.

Yi Zhang, Siddartha Khastgir, Xingyu Zhao

WMG, University of Warwick, Coventry, United Kingdom

Medical Image Classification Deep Learning AI Trustworthiness

Jul 1, 2026cs.MA

Calibrating the Instrument: Controllability of an LLM-Driven Synthetic Population

Generative Synthetic Populations (GSP) -- the convergence of population synthesis, agent-based modelling, and LLM agents -- are attracting growing interest for urban simulation and institutional communication research. Before any GSP instrument is used on a real population, a more basic question must be answered: does it respond to stimuli of known valence in an ordered, replicable, group-structured way? We call this controllability. We ask not whether a synthetic population tracks humans, but whether it tracks itself: whether the latent structure we impose on it is recovered in its own responses. This internal-validity question is logically prior to any claim about external validity, just as characterising an instrument's response function must precede using it to test a theory. We report SIVE (Synthetic Instrument Validation Experiment): a fictional municipality (Montelago) with 120 synthetic personas of known latent structure, exposed to seven conditions spanning strongly positive to strongly negative institutional communications about a water network. Seven pre-registered criteria, evaluated across a temperature sweep, jointly assess fidelity, stability, noise floor, specificity, sensitivity, and ordering. All seven pass at every temperature. A central finding turns a calibration failure into a diagnostic success: a message designed as "weakly positive" was identified by the instrument as functionally negative, traced to unresolved problems, uncertainty, and institutional passivity in its text; a redesigned version restored the expected ordering and interacts with agents' latent trust in unanticipated ways. A noise sub-experiment shows the instrument's intrinsic noise is roughly half the cross-agent estimate and stable across temperatures. Individual trajectories reveal coherent micro-dynamics that summary statistics obscure. Full data are available via an interactive explorer.

Mirko Degli Esposti

Department of Physics and Astronomy, University of Bologna

Population Dynamics Synthetic Data Institutions Controllability Responses AI Trustworthiness+1

Jul 1, 2026cs.HC

AI, Trust, and Teaming: The Humans-as-Handlers Approach for Autonomous and Opaque AI Systems

Artificial intelligence (AI) is becoming ubiquitous, and across domains, increasingly autonomous systems are carrying out tasks which raise significant ethical and legal challenges which demonstrate a need for strong human-machine teams rooted in trust. In this article, I argue that within highly impactful areas (such as medicine or warfighting) there are grounds for us initially treating autonomous and opaque systems as relevantly analogous to dogs (or other animals with which we have close relationships). Under this analogy, humans making use of these systems are not to be viewed as "users" or "deployers" of these systems, but instead take the role of "handlers". This recasting of roles shifts the way we view humans, AI-enabled and autonomous systems, and the relations between them, and moreover clarifies the clear and traceable lines of responsibility humans have for the outcomes brought about when using these systems. In developing this point, I clarify that the machine-animal analogy does admit disanalogous elements, but that its touch-points ground it as a starting point. I then explore how we can divest the humans-as-handlers approach of those aspects of our relationships with animals which are unfitting for how we engage with and make use of autonomous and AI-enabled systems. I conclude by arguing that the trajectory of human-machine teamings for autonomous and AI-enabled systems should be a state where we authentically view these not as artifacts which we simply make use of, but as collaborators with which we pursue complex goals and carry out complex tasks.

Nathan G. Wood

Human-Ai Collaboration Trustworthy Artificial Intelligence Artificial Intelligence Systems Human Agency AI Trustworthiness Species

Jul 1, 2026cs.SE

The Moving Target: A Longitudinal Audit of Trustworthiness Drift Across Twelve Checkpoints of Open-Source Chat LLMs

Model cards quote trust-benchmark scores without recording when they were measured, and the same number is routinely carried across successive checkpoints of one release line as if the model behind it had not shifted. We test whether it has shifted by auditing four open-source release lines, Yi, Qwen, Mistral, and Gemma, at three successive generations each, on a fixed basket of trust benchmarks under multiple prompt templates. Mean absolute adjacent-generation drift lands well above an independence-based no-drift reference null, and the gap persists when we drop a benchmark, drop a release line, or switch to strict scoring. We therefore conclude that a trust score attached to a release line should not be carried forward to the next checkpoint without remeasurement; it should instead be reported as a checkpoint-bound, dated artefact, which we package as a longitudinal model card. Closed APIs, larger models, canonical benchmark protocols, and fixed month-cadence rules lie outside the audited scope and require their own evaluation.

Zhichao Fan, Yanhang Li, Zexin Zhuang +2

University of Illinois Urbana-Champaign · Northeastern University · Southern Methodist University +2

Large Language Model Reliability AI Trustworthiness Model Auditing Intermediate Checkpoints Longitudinal Conditional Independence

Jun 30, 2026cs.CV

Trust the Prior (or Not): Uncertainty-Aware Abdominal Aortic Aneurysm Segmentation

Robust segmentation of intraluminal thrombus is critical for risk assessment in Abdominal Aortic Aneurysm, yet it remains challenging due to heterogeneous thrombus features and low contrast with surrounding non-enhanced tissues. Domain shifts induced by different Computed Tomography Angiography (CTA) protocols further inhibit multi-center generalization of deep learning models. To address these challenges, we propose a patient-specific framework that integrates discriminative learning with anatomically informed priors. Our approach introduces two key components: (1) a patient-specific intensity normalization based on a Gaussian Mixture Model of local anatomy, and (2) an Uncertainty-Gated Anatomical Attention module that incorporates spatial priors while adaptively modulating their influence according to voxel-wise confidence. This design allows for anatomical guidance in ambiguous regions while suppressing unreliable priors. The proposed method achieves state-of-the-art performance on in-distribution test data and substantially outperforms existing alternatives in generalization to external multi-center CTA data, while remaining interpretable through an explicit separation of visual and anatomical evidence.

Erich Robbi, Daniele Ravanelli, Andrea Passerini

Department of Computer Science University of Trento Trento, Italy · Medical Physics Unit Santa Chiara Hospital Trento, Italy

Semi-Supervised Medical Image Segmentation Coronary Angiography AI Trustworthiness

Jun 30, 2026cs.CL

Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust

Language models have changed from unreliable text generators to highly-capable large models with trillions of parameters. Capability increases come hand-in-hand with increases in scale, making understanding the internal representations of models more challenging. Since millions of users increasing rely on language models to interact with external tools or make decisions in medium or high-stakes scenarios, we need to establish control over model behavior and know when to trust model outputs. In this paper, we discuss our contributions on harnessing the latent spaces by proposing steering vectors for control and developing latent space-based model calibrators for trust. Together, our contributions help demystify the latent spaces of language models and offer new insights into how to harness model internals to build more trustworthy language technology.

Nishant Subramani

Carnegie Mellon University, Language Technologies Institute

AI Trustworthiness Steering Latent Space Text Generation

Jun 30, 2026cs.AI

Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy

Medical Artificial Intelligence (AI) is widely expected to transform clinical practice, yet the decision-making processes of many Machine Learning (ML) models remain opaque. Explainability has been advanced as a partial remedy to clarify why AI generates predictions, particularly in high-stakes contexts. Despite ongoing efforts, debates on what constitutes an adequate medical explanation remain unsettled. Yet, explanation has long been a central topic of inquiry in the philosophy of science and medicine. The insights developed in these fields, however, have been largely overlooked in contemporary explainable AI (XAI) research, leaving its foundational assumptions insufficiently examined. To address this gap, this paper develops a critical review at the intersection of philosophy of science and XAI. It examines prevailing accounts of what counts as an explanation in the health sciences and assesses their adequacy for informing XAI in medicine, arguing that they provide necessary conditions for a philosophically grounded approach to explainability in this domain. Building on this foundational philosophical literature, the discussion identifies three central axes of analysis: the role of causality in medical reasoning, the epistemic and relational dimensions of medical trust, and the criteria of explanatory adequacy as shaped by the pragmatic needs of diverse stakeholders. By integrating philosophical analysis with current developments in medical AI, the paper outlines principles for designing XAI systems that offer explanations that are not only epistemically robust but also aligned with the epistemic and practical requirements of clinical decision-making, shaping ongoing debates in medical XAI toward underexplored conceptual foundations.

Martina Mattioli, Marcello Pelillo

Explainable Artificial Intelligence Xai Causal Reasoning Scientific Discovery AI Trustworthiness

Jun 29, 2026cs.RO

Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models

Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning. However, existing RL methods typically require external environmental feedback, relying on predefined success signals to guide policy updates. In this work, we show that VLA models possess useful internal evaluative capabilities: in discrete-action VLAs, trajectories with higher generation confidence are significantly more likely to succeed. Based on this observation, we introduce T^2VLA (Test-time VLA), an architecture-agnostic test-time RL framework that enables VLA models to achieve self-bootstrapping policy improvement. Instead of relying on external rewards, T^2VLA leverages trajectory-level similarity to high-confidence expert demonstrations as an intrinsic reward signal. In addition, we propose a Confidence-Driven Dual Expert Bootstrapping mechanism, which dynamically balances a Local Pseudo-Expert for exploration and a Global Expert Pool for training stability. Extensive experiments on the LIBERO and RoboTwin benchmarks show that T^2VLA consistently outperforms supervised baselines and approaches oracle RL performance with ground-truth rewards, achieving effective improvement without external reward feedback. Furthermore, T^2VLA adapts to distinct VLA paradigms, including both OpenVLA-OFT and the pi series.

Siyao Chen, Jiakang Yuan, Jiaxin Wang +1

College of Future Information Technology, Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · MoShen Intelligence, Shanghai, China

AI Trustworthiness

Jun 28, 2026cs.CR

The Calibrated Deepfake Trust Score (CDTS): Competence-Coupled Trust Degradation Across Deepfake Detectors

Modern deepfake detectors are rarely consumed as bare classifiers. In moderation, provenance, and verification pipelines their output probability is read as a degree of trust, so its calibration matters as much as raw accuracy. We reframe deepfake detection as a calibrated, self-auditing trust instrument, the Calibrated Deepfake Trust Score (CDTS), and identify what governs its trustworthiness. Our central finding is a competence-calibration coupling: the calibration of the trust score degrades as the detector's discriminative competence falls. We establish it across 32 configurations (pooled Pearson r = -0.81), demonstrate it within a single dataset, reinforce it by inducing low competence directly, and replicate it on a fourth held-out dataset the detectors never trained on. It holds across three architecturally distinct detectors, two convolutional networks and a CLIP vision transformer (r = -0.88, -0.83, -0.86). The result is also deployable: a single calibrator frozen on in-domain data fails on exactly the low-competence generators the coupling flags (its error tracks competence at r = -0.98), and competence is estimable without labels, so a label-free monitor flags calibration risk on unseen generators and routing source-batches on a reference-free competence estimate lowers overall AURC and improves the low-to-mid coverage operating region relative to confidence-based routing. The same competence factor also drives calibration inequity across demographic subgroups (distinct from accuracy inequity) and explanation faithfulness. We therefore argue that detector trustworthiness is organized by competence as a shared driver, that competence is the right quantity to estimate and condition on, and that trust scoring must be competence-aware. We offer the CDTS wrapper as the mechanism, and report openly where the unification is tight and where it is architecture-specific.

Md Anas Biswas

School of Computing, University of Portsmouth, Portsmouth, United Kingdom

Deepfake Detection AI Trustworthiness Discriminative

Jun 27, 2026cs.CR

Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare

Agent-based AI has enabled the automation of tasks by exposing application tools and resources to large language models (LLMs). However, to improve scope and accuracy, agents are often given access rights that exceed those of ordinary users, introducing significant security risks. AI is routinely integrated into applications with a disregard to security, risking data exposure and breaching regulations. This paper applies the AI Trust, Risk, and Security Management (TRiSM) framework to a medical report-generation application to demonstrate how an insecure agent workflow can be transformed into security-conscious agentic workflow. Both workflows were evaluated across five LLMs (Claude Haiku 4.5, GPT-4.1-nano, GPT-4.1-mini, GPT-5.4-mini, and Gemini 2.5 Flash) on two report types, totalling 800 generations and 500 attack scenarios including RAG poisoning, data-field injection, and client-side network injection. The TRiSM-guided agentic workflow reduced mean attack success rates from 31% to 10% for RAG poisoning and from 42% to 25% for data-field injection, while eliminating the network injection vector entirely through server-side prompt construction. Furthermore, report accuracy increased by 14 percentage points (72.5% to 86.5%) with the agentic workflow, demonstrating a secure design which provides more reliable outputs. This paper contributes to knowledge by demonstrating least-privilege, defence in depth agentic workflows improving security and accuracy, while also highlighting model choice is a necessary architectural consideration.

Liam Kearns

AuraQ Malvern Worcestershire UK

Trustworthy Artificial Intelligence Agentic Workflows Security Evaluation AI Trustworthiness Attack-Success Rate Medical Report Generation+1

Jun 26, 2026cs.CV

TRUST: Efficient Abdominal Trauma Recognition via Image-to-Ultrasound-Video Transfer Learning

Abdominal ultrasound is indispensable for rapid, noninvasive trauma triage. However, interpreting the subtle dynamic cues embedded in continuous scanning is time-intensive and operator-dependent. Parameter-Efficient Image-to-Video Transfer Learning (PEIVTL), which efficiently adapts pre-trained image models to the video domain, notably through visual-textual alignment, offers a promising paradigm for ultrasound video analysis. Nevertheless, substantial spatiotemporal and semantic variations arising from physician-dependent scanning practices continue to limit the effectiveness and generalizability of this framework. We propose TRUST, a scan-aware PEIVTL framework that explicitly models fine-grained spatiotemporal variations to enable reliable ultrasound video understanding. First, we introduce a Cross-Frequency Collaborative Adapter (CFCA) that establishes mutual constraints between low- and high-frequency components, enhancing discriminative spatial feature extraction under heavy speckle corruption. Second, we design a Multi-Granularity Motion-Aware (MGMA) module that integrates local temporal convolutions with motion-prior-guided global self-attention, jointly capturing stable intra-view patterns and abrupt inter-view transitions to characterize complex scanning dynamics. Third, a Visual Query Semantic Aggregation (VQSA) module dynamically generates text prototypes conditioned on visual features, enabling adaptive visual-textual alignment robust to intra-class variability under diverse scanning conditions. Experiments on in-house ultrasound trauma datasets demonstrate that TRUST outperforms state-of-the-art methods by 9.63% with superior computational efficiency.

Enguang Wang, Hao Zhou, Shuo Gao +2

School of Biological Science and Medical Engineering, Southeast University, Nanjing, China · Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing, China · State Key Laboratory of Digital Medical Engineering, Southeast University, Nanjing, China +1

Ultrasound Clinical Ultrasound Dataset Vision Sensors Triage AI Trustworthiness

Jun 25, 2026cs.CV

Confidence-Aware Tool Orchestration for Robust Video Understanding

Video reasoning language models implicitly assume that every input frame is equally reliable. This leads to what we term the Blind Trust Problem: under realistic perturbations such as motion blur, glare, or occlusion, frontier video reasoning models can suffer 15-30%p accuracy drops on real-world embodied benchmarks, while remaining unaware that their visual evidence has been degraded. To address this challenge, we propose Robust-TO, an agentic video understanding framework that explicitly integrates per-frame trustworthiness into every stage of reasoning. Robust-TO organizes heterogeneous visual perception tools under a unified evidence interface. Each tool receives a sub-query derived from the original question and a set of trustworthy frames selected by the reliability-relevance score. It returns evidence in a shared format: a concrete prediction (e.g., a bounding box, motion trajectory, recognized text, or action label), temporal grounding, and a calibrated reliability score. During reasoning, these calibrated scores guide evidence weighting in a three-tier synthesis process (high/medium/low) and define a confidence-cost GRPO reward that jointly optimizes correctness, evidence reliability, and efficiency. On two video reasoning benchmarks spanning eight tasks, Robust-TO achieves 56.4% average accuracy on clean inputs, surpassing the strongest open-source baseline by 10.6%p and outperforming Gemini-2.5-Pro (46.2%). Under five realistic corruption types, Robust-TO maintains 54.3% average accuracy, 5.8%p above the strongest open-source baseline, while exhibiting the smallest clean-to-corrupted accuracy drop among all compared methods.

Yangfan He, Yujin Choi, Jaehong Yoon

1NTU Singapore · University of Minnesota, Twin Cities · 3UNIST

Fine-Grained Video Understanding Video Agent Visual Evidence AI Trustworthiness

Jun 25, 2026cs.CR

Fortress and Gatekeeper: Theorizing Transitive Trust in Third-Party Cybersecurity Risk Governance

Third-party vendors, such as analytics platforms, cloud services, identity providers, and software suppliers, are increasingly embedded in digital service delivery. While these arrangements enable scale and specialization, they also move customer data and security-relevant practices into environments that customers rarely see, select, or evaluate. This paper examines this problem through a document analysis of the November 2025 OpenAI-Mixpanel security incident. The incident serves as an illustrative case for showing how a security event in a vendor environment can become a governance and accountability problem for the focal organization that maintains the customer relationship. Drawing on organizational trust research and agency theory, the paper argues that third-party cybersecurity risk is both a trust relationship and a delegation problem. Customers trust the visible service provider, while the provider relies on vendors whose security practices are only partially visible and controllable. The paper develops the concept of transitive trust, where customer trust in a digital service depends on the security practices of vendors authorized by that service provider. It then presents the Fortress and Gatekeeper framework, which explains cybersecurity governance boundaries through trust and data flows rather than formal organizational ownership alone. The analysis develops four propositions concerning vendor integration, metadata exposure, vendor assurance, and data proliferation. The paper contributes to cybersecurity governance scholarship by explaining how delegated data processing creates customer-facing accountability and by identifying implications for vendor tiering, data classification, contractual design, continuous assurance, and data minimization.

Yijun Chen, Misita Anwar

Macquarie University, NSW, Australia · Monash University, Swinburne University of Technology, VIC, Australia

Cybersecurity Governance AI Trustworthiness Gating

Jun 24, 2026cs.AI

Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions

AI companions powered by large language models increasingly interact with cognition-developing users, including children and adolescents, creating risks that may accumulate over time. Existing safety evaluations largely rely on single-turn or short-session tests, which cannot capture risks that emerge only through prolonged interaction. To address this gap, we propose TSJ (Theater-Stage-Judge), a longitudinal framework combining persona-driven user simulation, dynamic psychological-state updating and retrospective evaluation. We evaluate six mainstream models across four developmental stages, twenty-four risk dimensions and three psychological-vulnerability personas, covering 12,960 simulated person-day interactions. TSJ shows that short-horizon testing systematically underestimates developmental risks, for which TSJ yields a stable risk estimate only after 140 turns within prolonged simulated relationships. Applying TSJ further identifies early childhood and emerging adulthood as the most vulnerable stages, with cognitive trust and emotional dependency as the weakest domains. TSJ provides a scalable methodology for longitudinal cognitive developmental risk evaluation in AI companion systems.

Kaicheng Shen, Lingyu Li, Wen Wu +3

Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · School of Computer Science and Technology, East China Normal University, Shanghai, China

Artificial Intelligence Companions User Simulation Developmental Trajectories AI Trustworthiness Risk Long-Term

Jun 23, 2026cs.AI

TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. Existing memory agents actively update external memory through generated write, revise, and delete operations, but these updates may omit important information, corrupt existing memory, or introduce unsupported hallucinated content. Once stored, such errors become persistent system-state failures that can affect future reasoning and generation. In this paper, we propose TrustMem, a framework designed to improve the trustworthiness of memory consolidation. TrustMem relies on a Memory Transition Verifier to evaluate the transition process of memory updates in terms of coverage, preservation, and faithfulness. It further constructs preference pairs among candidate updates under the same memory state, enabling preference-guided reinforcement learning to directly optimize memory updating behaviors. Extensive experiments demonstrate that TrustMem improves both memory utility and reliability: it achieves state-of-the-art results across MemoryAgentBench, HaluMem, and the Mem-alpha validation set, improves HaluMem memory extraction by 12.14 F1 points, and reduces transition-level omission, corruption, and hallucination by 40.1%, 79.1%, and 50.0%, respectively, compared with the strongest baseline for each error type.

Tianyu Yang, Sudipta Paul, Vijay Srinivasan +2

AI Center-Mountain View, Samsung Electronics · University of Notre Dame

Agentic Memory Long-Term Memory Large Language Model Agents AI Trustworthiness Memoryagentbench

Jun 23, 2026cs.AI

The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing

Autonomous AI systems are transitioning from advisory to autonomous roles for medication prescriptions. Recent United States bill H.R. 238 and Utah's prescription-renewal pilot both authorize AI to prescribe medications in an agentic capacity. While some regulatory guidelines suggest aggregate model performance metrics for clearance, they do not require i) calibrated per-prediction confidence for action-gated thresholds, ii) differentiated communication of uncertainty arising from model ignorance (epistemic) versus genuine clinical ambiguity (aleatoric), and iii) inferential transparency at the moment of decision that allows for liability allocation. Here, we present a regulatory and technical argument (tested with a survey of 136 U.S. prescribing clinicians) positioning these as minimum architectural requirements for safe autonomous prescribing. Our results suggest prescribing clinicians i) would not permit autonomous prescribing without a calibrated confidence-based escalation mechanism, ii) preferred a competing-options summary when uncertainty was aleatoric but shifted to abstention when uncertainty was epistemic, and iii) were only willing to accept additional liability when inferential transparency enabled a substantive judgment under acknowledged uncertainty. These findings indicate our recommended architectural features would encourage higher rates of clinician adoption, largely through collapsing much of what "autonomy" conventionally means. A system meeting these requirements would function less as an autonomous agent and more as a heavily supervised decision-support tool. As legislation and state pilots proceed, our technical argument backed by clinician perspectives provides opportunities for regulation to constrain the degree of autonomy ethically granted to AI in prescribing while aligning liability with the institutional actors who control system design and deployment.

Eileanor LaRocco, Sarah Tan, Adarsh Subbaswamy +4

University of Virginia · Cornell University · University of Maryland, Baltimore +1

Medication Leaflet Clinician Trust AI Trustworthiness Abstention Uncertainty Agentic

Jun 23, 2026eess.AS

Breaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training

Recent end-to-end models for EEG-guided target speech extraction report impressive results, underscoring potential for neuro-steered hearing technologies. However, our analysis reveals that high within-trial performance can be driven by trial-specific EEG structure that acts as shortcuts for target selection, leading to poor generalization on unseen trials. To overcome this gap, we propose TRUST-TSE, a two-stage framework to mitigate shortcut learning. By introducing contrastive pretraining with attended-speaker negative sampling, we encourage the EEG encoder to capture fine-grained EEG--speech alignment while suppressing trial-identity cues. We also employ a confidence-weighted extraction objective based on EEG--source similarity to guide extraction using the learned representations. Experiments on KUL and DTU datasets show that TRUST-TSE outperforms end-to-end baselines under strict cross-trial protocols, addressing a key reliability bottleneck of existing approaches.

Wonchul Shin, Inyong Choi, Kyogu Lee

Department of Intelligence and Information, Seoul National University, Republic of Korea · Department of Communication Sciences and Disorders, University of Iowa, United States · Interdisciplinary Program in Artificial Intelligence, Seoul National University, Republic of Korea +1

Target Speaker Extraction Electroencephalography Auditory Attention Multi-Stage Training Shortcut Learning AI Trustworthiness

Jun 22, 2026physics.data-an

Where Is My Physics Wrong? Localized and Identifiable Discovery of Model Discrepancy

Hybrid models combine trusted physics with data-driven correction, but a physical model is rarely wrong everywhere or in the same way. The key diagnostic question is local: where does the model fail, what missing mechanism explains the failure, and is the evidence statistically real? Existing sparse-discovery and discrepancy-learning methods usually fit one global correction, which can spread a local error into clean regimes, bias trusted physical parameters, and provide no calibrated significance for selected terms. We introduce LISDD, Localized, Identifiable Sparse Discovery of Discrepancy, a framework that localizes model error to an operating regime, identifies a sparse symbolic form for the missing mechanism, and certifies the discovery with an exact finite-sample test. LISDD fits the known physics on an automatically detected clean regime, flags discrepant regions with a calibrated residual-energy statistic, selects the local missing term by exhaustive holdout over a candidate library, and confirms significance with a sample-split

F

-test. A false-discovery-rate extension handles multiple discrepant regions with different missing mechanisms. In controlled experiments, LISDD keeps physical-parameter bias at 0.002 versus 0.43 for global-discrepancy and black-box baselines, raises localization

F_1

from 0.44 to 0.80, recovers the correct symbolic form with probability one, attains exact detection, and controls the multi-region false-discovery rate while recovering every planted mechanism. The result is a calibrated diagnostic tool for grey-box building-energy models when a fixed physical law silently breaks in one operating regime.

Yifan Wang

Department of Mechanical Engineering, McGill University, QC, H3A 2T7, Canada

Discrepancy Model Discovery False Discovery Rate Evidence Conflict AI Trustworthiness

Jun 19, 2026cs.CV

EnTrust: Modeling Inter-Modal Conflict for Trustworthy Multimodal Medical Image Analysis

Multimodal medical imaging fuses complementary anatomical and functional information, yet modalities frequently disagree in pathologically heterogeneous regions. Current segmentation models handle this in one of two inadequate ways: deterministic fusion that averages away disagreement, or post-hoc uncertainty estimation decoupled from the fusion process that produces it. Both obscure the clinically critical question: why is this prediction unreliable? We present EnTrust, a framework that treats inter-modal conflict as the primary source of predictive uncertainty. Our EnFuse module decomposes multimodal features into three disentangled components: shared anatomical consensus (F_c), modality-specific cues (F_{u,m}), and spatially localized conflict signals (F_{cf}), with independence enforced via a cross-covariance objective. This structured decomposition conditions SegDiff, a diffusion-based generative segmentation model whose sampled hypotheses diverge specifically in regions of modal disagreement. TrustMap then translates this hypothesis divergence into calibrated, pixel-wise uncertainty using ensemble entropy, conflict-guided perturbation probing, and a learned calibration head, enabling clinicians to understand not only where predictions are uncertain, but why. Across four benchmarks spanning brain, cardiac, lesion, and oncology domains, EnTrust achieves state-of-the-art segmentation accuracy while reducing calibration error by 40% compared to the strongest baseline. Notably, it outperforms 5x deep ensembles using a single model at roughly half the memory footprint. Code and checkpoints are available at https://github.com/GenMI-Lab/EnTrust.git.

Dwarikanath Mahapatra, Abhijit Das, Behzad Bozorgtabar +5

Khalifa University, Abu Dhabi, UAE. · MBZUAI, Abu Dhabi, UAE. · Aarhus University, Denmark. +5

Pixel-Level Prediction Disagreement AI Trustworthiness

Jun 18, 2026cs.CR

FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming

Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation developed with financial experts. FinRED uses a novel two-level taxonomy mapping global standards (e.g., FATF and EU DORA) to threats ranging from regulatory evasion to complex fraud, integrated with a scalable pipeline that converts real financial documents into context-rich red-teaming Behavioral Prompts (seeds) through an expert-defined schema. Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation. We also provide an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28 to 12. Aligned with internationally adopted risk-management and information-security standards (e.g., ISO/IEC 27001), FinRED is deployed in South Korea's Financial Security Institute (FSI) regulatory sandbox for generative AI security evaluation in real financial services. To mitigate dual-use risks, the dataset, generation pipeline, prompt template, and evaluation framework are gated for qualified researchers at https://github.com/selectstar-ai/FinRED-paper and https://huggingface.co/datasets/datumo/FinRED.

Chaeyun Kim, Daeyoung Park, Junghwan Kim +4

DATUMO INC., Republic of Korea · Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea · Financial Security Institute (FSI), Republic of Korea

Red-Teaming Large Language Model Safety Large Language Model Evaluation Artificial Intelligence Risk AI Trustworthiness

Jun 18, 2026cs.RO

Toward Machine Risk Perception: Integrating Trust Calibration and Precursor-Based Risk Estimation for Humanoid

Humanoid robots are emerging as co-workers in smart manufacturing, yet their dynamic, human-like movements introduce safety risks that differ fundamentally from those of fixed or wheeled robots. Conventional safety paradigms based on reactive force or distance limits fail to capture the sequential, uncertain nature of humanoid failures. This study proposes a precursor-driven, trust-calibrated framework to enable proactive humanoid risk perception. Accident evolution is modeled through sequential precursor cues using a Logistic-Exponential (LE) formulation that couples logistic escalation from diverse precursors with exponential decay for temporal dissipation. Trust is defined as the inverse of the estimated accident probability, allowing humanoids to adapt behavior in real time, reducing aggressiveness when risk intensifies, and restoring confidence as stability returns. A multi-source dataset of 126 documented events and 241 precursors revealed twelve dominant accident modes, most evolving through overlapping cues within one second. A simulated case study ("fall-onto-human") demonstrated how the LE-Trust coupling can trigger early intervention and prevent collapse. The results advance humanoid safety from static thresholds toward dynamic, evidence-based inference, establishing a foundation for risk-aware and trustworthy human-robot collaboration in Industry 5.0 environments.

He Wen

AI Safety Lab, Bailey College of Engineering & Technology, Indiana State University, Terre Haute, IN

Human-Robot Collaboration Accidents AI Trustworthiness Perception

Jun 16, 2026cs.AI

Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding

Graphical user interface (GUI) grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordinates. On-policy self-distillation (OPSD) is a promising post-training approach for this coordinate-sensitive task, since it provides dense token-level teacher signals beyond hard coordinate labels. However, naive OPSD is not well suited to GUI grounding: OPSD evaluates the teacher on student-generated prefixes, the quality of coordinate-token teacher signals can degrade when the prefix has already deviated from the target coordinate, leading to unreliable teacher signal. To mitigate this, We propose quality-aware self-distillation for VLM-based GUI grounding, which improves coordinate-token teacher-signal quality through soft correctness-aware gating and teacher-probability scaling. The soft correctness-aware gate checks whether the teacher's current coordinate-token prediction can still be completed into the ground-truth box under the student-generated prefix. If not, the corresponding teacher signal is down-weighted. Teacher-probability scaling then uses the teacher's confidence as a lightweight factor to further calibrate the strength of the gated supervision. A key empirical finding is that neither component alone improves overall performance, whereas combining them consistently improves performance. This suggests that the two mechanisms play complementary roles: correctness-aware gating suppresses unreliable coordinate-token supervision, while teacher-probability scaling calibrates the strength of the remaining signals. Experiments across six GUI grounding benchmarks show that our method consistently improves the base model and outperforms strong baselines.

Jingyuan Huang, Zuming Huang, Yucheng Shi +4

University of Georgia · 2INFLY Tech · *This work was done during an internship at INFLY Tech. +2

Graphical User Interface Self-Distillation Framework Teacher AI Trustworthiness

Jun 16, 2026cs.HC

AI Adoption Across a Multinational Workforce: Sociotechnical Conditions for GenAI Acceptance in Human Resources

Generative AI (GenAI) deployment in the workplace is accelerating rapidly. Nevertheless, questions of who adopts, who benefits, and who is left behind and why are still understudied. In this paper, we investigate these dynamics in the context of a multinational tech company transitioning from a legacy Human Resources (HR) search system to a GenAI-supported system, analyzing search log data, survey data (n=25), and ten semi-structured interviews. Our findings show that adoption depended on the fit between the GenAI system's design assumptions and employees' work positionalities (role, spoken language, tenure). Further, we find that employees' trust in GenAI answers was built through source-checking, comparison among systems, and seeking input from colleagues or HR when in doubt. Our contribution is twofold. First, we provide empirical evidence of workplace GenAI adoption during a live organizational transition, showing that adoption is influenced by factors such as situational fit, search literacy, and trust calibration. It is also further shaped by knowledge conditions such as the system's content quality, employee training, and guidance. Second, we translate these findings into design considerations for inclusive deployment and adoption in high-stakes environments such as HR. We argue that organizations should design systems considering the role and context-sensitive benefits they yield to different social groups. They also need to treat the organizational knowledge infrastructure as AI infrastructure to improve the accountability and usability of GenAI systems

Dalia Ali, Maria José Rodríguez Velázquez, Manoel Horta Ribeiro +2

Technical University of Munich · Princeton University · University of Michigan

Socio-Technical Systems Generative Artificial Intelligence Artificial Intelligence Systems Interviews AI Trustworthiness

Jun 15, 2026cs.LG

TCHG: Tri-Trust Conditioned Heterogeneous Graph Learning for Reliable Dynamic Trust Prediction

Trust prediction infers latent user-user trust relations and provides important support for social recommendation, fake-review and manipulation detection, and risk identification. Graph neural networks have become a prominent approach to trust prediction because of their ability to learn network structures and complex trust dependencies. However, existing methods often rely on a unified representation of trust signals and do not disentangle heterogeneous trust evidence into separate evidence channels, failing to exploit the distinct roles that different evidence channels should play during trust modeling. To address this gap, this paper argues that trust evidence should not be treated as an undifferentiated input, but should be decomposed and used as functional control factors over graph propagation. We propose TCHG, a tri-trust conditioned heterogeneous graph learning framework that decomposes trust evidence into three channels and assigns them distinct functional roles in propagation: entity reliability governs message admission, interaction-behavior reliability modulates propagation strength, and contextual trust adjusts the propagation mode through context-conditioned operator selection. Since the three evidence channels evolve at different temporal scales, TCHG maintains independent temporal states with non-uniform decay rates to prevent rapidly changing contextual signals from overwriting slowly accumulated entity reliability. It further predicts trust probability and calibrates the output probability, improving predictive confidence under sparse or conflicting evidence. Extensive experiments on multiple public trust datasets show that TCHG achieves effective and reliable trust prediction compared with representative trust prediction and heterogeneous graph baselines.

Bohao Liao, Boyu Deng, Qipeng Song +2

School of Telecommunication Engineering, Xidian University, Xi’an, 710071, Shaanxi, China · National Key Laboratory of Multi-domain Data Collaborative Processing and Control, Beijing, 100141, China · School of Cyber Engineering, Xidian University, Xi’an, 710071, Shaanxi, China

Log-Ratio-Based Gaussian Trust Weight Text-Attributed Graph AI Trustworthiness Recommendation

Jun 14, 2026cs.AI

TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI

AI agents increasingly access external models, tools, and services through Agentic Routing Infrastructure (ARI) to manage the overhead of heterogeneous interfaces and fragmented subscriptions. Yet, the architecture of ARI introduces fundamental trust risks: it obtains plaintext access to agent queries and service responses, while leaving agents unable to verify that their queries are routed to intended service providers or that requests and responses remain untampered. To address this problem, we present TrustedARI, the first trust-native agentic routing infrastructure for agentic AI. Architecturally, TrustedARI is built upon three core innovations: (i) an ARI-adapted three-party TLS handshake that enables the agent and ARI to jointly authenticate the service provider through role-specific distribution of TLS key materials; (ii) a privacy-preserving query-construction protocol that allows the agent and ARI to collaboratively construct well-formed queries without exposing their respective private inputs; and (iii) a verifiable billing protocol that supports fair usage-based settlement while preserving the integrity and confidentiality of service responses. We implemented and extensively evaluated a prototype of TrustedARI to validate its performance. Experiments confirm that TrustedARI is highly efficient: our ARI-adapted handshake protocol reduces communication overhead by 39.34% compared to the existing three-party TLS handshake. Furthermore, the privacy-preserving query-construction protocol imposes negligible overhead-averaging 0.19 seconds in computation time and 0.58 MB in communication costs-while the verifiable billing protocol speeds up proof generation by 28.20x. Crucially, TrustedARI is readily deployable without any modification to the service providers.

Qi Li, Zhenhua Zou, Shuo Li +2

Tsinghua University

Trustworthy Artificial Intelligence AI Trustworthiness Lidar