LLM Agent Reliability

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

90 papers in the last four weeks, up 109% on the four weeks before. 0.9% of all new papers.

Jul 13Week of Sep 28

Latest papers 558

Jan 11, 2026cs.CL

LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents

As LLMs move from text completion toward autonomous agents, they remain constrained by the standard chat interface, which lacks private working memory. This raises a fundamental question: can agents reliably perform interactive tasks that depend on hidden state? We define Private State Interactive Tasks (PSITs), which require agents to generate and maintain hidden information while producing public responses consistent with a fixed hidden state. We show theoretically that any agent restricted to the public conversation history cannot both keep the secret unresolved in the transcript and respond consistently with a fixed hidden state in PSITs, yielding an architectural impossibility theorem. To empirically validate this limitation, we introduce a self-consistency testing protocol that evaluates whether agents can maintain a hidden secret across forked dialogue branches. Standard chat-based LLMs and retrieval-based memory baselines fail this test regardless of scale, demonstrating that semantic retrieval does not enable true state maintenance. To address this, we propose a novel architecture incorporating an explicit private working memory; we demonstrate that this mechanism restores consistency with a fixed hidden state, establishing private state as a necessary component for PSIT-capable language agents. Our code is available at https://github.com/chandar-lab/Hangman

Davide Baldelli, Ali Parviz, Amal Zouaq +1

Chandar Research Lab · LAMA-WeST Lab · Mila – Quebec AI Institute +2

LLM Agent Memory LLM Agent Reliability

Dec 15, 2025cs.MA

AOI: Context-Aware Multi-Agent Operations via Dynamic Scheduling and Hierarchical Memory Compression

Cloud-native systems have made operational work both more powerful and harder to automate: incidents unfold across microservices, logs and metrics arrive faster than operators can inspect them, and recovery actions must be coordinated without losing the causal context that makes them safe. We present AOI (AI-Oriented Operations), a context-aware multi-agent framework for autonomous IT operations. AOI separates operational responsibility across an Observer, a read-only Probe, and a guarded Executor, and connects them through dynamic scheduling and a hierarchical memory system with LLM-based context compression. This design turns long-running incident response into an iterative loop of observation, evidence gathering, safe intervention, and memory update. Across AIOpsLab simulations and real-world Loghub-derived scenarios, AOI improves task success to 94.2%, reduces mean time to resolution by 34.4% relative to the strongest baseline, and compresses operational context by 72.4% while preserving 92.8% of diagnostic information. Ablations show that these gains come from the combination of agent specialization, adaptive scheduling, and memory-aware compression rather than from any single module alone. The results suggest that autonomous operations systems can move beyond alert classification toward reliable, context-preserving recovery in complex infrastructure.

Zishan Bai, Hanxuan Chen, Jiayi Gu +9

Columbia University · Hunan University · Central University of Finance and Economics +8

Multi-Agent Orchestration LLM Context Management Memory-Augmented Agents LLM Agent Reliability

Dec 6, 2025cs.AI

Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation

Echocardiography interpretation requires integrating multi-view temporal evidence with quantitative measurements and guideline-grounded reasoning, yet existing foundation-model pipelines largely solve isolated subtasks and fail when tool outputs are noisy or values fall near clinical cutoffs. We propose Echo-CoPilot, an end-to-end agentic framework that combines a multi-perspective workflow with knowledge-graph-guided measurement selection. Echo-CoPilot runs three independent ReAct-style agents, structural, pathological, and quantitative, that invoke specialized echocardiography tools to extract parameters while querying EchoKG to determine which measurements are required for the clinical question and which should be avoided. A self-contrast language model then compares the evidence-grounded perspectives, generates a discrepancy checklist, and re-queries EchoKG to apply the appropriate guideline thresholds and resolve conflicts, reducing hallucinated measurement selection and borderline flip-flops. On MIMICEchoQA, Echo-CoPilot provides higher accuracy compared to SOTA baselines and, under a stochasticity stress test, achieves higher reliability through more consistent conclusions and fewer answer changes across repeated runs. Our code is publicly available at https://github.com/moeinheidari7829/Echo-CoPilot.

Moein Heidari, Ali Mehrabian, Mohammad Amin Roohi +5

The University of British Columbia, Vancouver, BC, Canada · Rutgers Cancer Institute, New Brunswick, NJ, USA

Medical VQA Echocardiography Ultrasound Imaging Multi-Agent Systems LLM Agent Reliability

Nov 21, 2025cs.AI

Bridging Symbolic Control and Neural Reasoning in LLM Agents -- The Structured Cognitive Loop

Large language model agents suffer from architectural fragilities such as entangled reasoning and execution, memory volatility, and uncontrolled action sequences. We introduce Structured Cognitive Loop (SCL), a modular agent architecture that separates cognition into Retrieval, Cognition, Control, Action, and Memory (R-CCAM). SCL introduces Regulation as a dedicated governance layer through which Soft Symbolic Control applies symbolic constraints to probabilistic inference, while Control remains a distinct deterministic runtime engine for duplicate-call prevention, error limits, and termination judgment. Through multi-step conditional reasoning experiments, we show that SCL achieves zero policy violations, prevents redundant tool calls, and maintains complete decision traceability. We position SCL within hybrid intelligence, distinguish it from prompt-centric, memory-only, and neuro-symbolic approaches, and derive three design principles for trustworthy agents: modular decomposition, adaptive symbolic governance, and transparent state management. With an open-source implementation and a live GPT-4o-powered travel planning agent, this work offers a practical path toward reliable, explainable, and governable LLM agents.

Myung Ho Kim

JEI University

Neuro-Symbolic Reasoning AI Agent Governance LLM Agent Reliability

Nov 19, 2025cs.AI

Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response

Large language models (LLMs) promise to accelerate incident response in production systems, yet single-agent approaches generate vague, unusable recommendations. We present MyAntFarm.ai, a reproducible containerized framework demonstrating that multi-agent orchestration fundamentally transforms LLM-based incident response quality. Through 348 controlled trials comparing single-agent copilot versus multi-agent systems on identical incident scenarios, we find that multi-agent orchestration achieves 100% actionable recommendation rate versus 1.7% for single-agent approaches, an 80 times improvement in action specificity and 140 times improvement in solution correctness. Critically, multi-agent systems exhibit zero quality variance across all trials, enabling production SLA commitments impossible with inconsistent single-agent outputs. Both architectures achieve similar comprehension latency (approx.40s), establishing that the architectural value lies in deterministic quality, not speed. We introduce Decision Quality (DQ), a novel metric capturing validity, specificity, and correctness properties essential for operational deployment that existing LLM metrics do not address. These findings reframe multi-agent orchestration from a performance optimization to a production-readiness requirement for LLM-based incident response. All code, Docker configurations, and trial data are publicly available for reproduction.

Philip Drammeh

Independent Researcher

Multi-Agent LLM Systems LLM Agent Orchestration LLM Agent Evaluation Cybersecurity LLM Agent Reliability

Oct 24, 2025cs.AI

CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation

Chest X-ray (CXR) plays a pivotal role in clinical diagnosis, and a variety of task-specific and foundation models have been developed for automatic CXR interpretation. However, these models often struggle to adapt to new diagnostic tasks and complex reasoning scenarios. Recently, LLM-based agent models have emerged as a promising paradigm for CXR analysis, enhancing model's capability through tool coordination, multi-step reasoning, and team collaboration, etc. However, existing agents often rely on a single diagnostic pipeline and lack mechanisms for assessing tools' reliability, limiting their adaptability and credibility. To this end, we propose CXRAgent, a director-orchestrated, multi-stage agent for CXR interpretation, where a central director coordinates the following stages: (1) Tool Invocation: The agent strategically orchestrates a set of CXR-analysis tools, with outputs normalized and verified by the Evidence-driven Validator (EDV), which grounds diagnostic outputs with visual evidence to support reliable downstream diagnosis; (2) Diagnostic Planning: Guided by task requirements and intermediate findings, the agent formulates a targeted diagnostic plan. It then assembles an expert team accordingly, defining member roles and coordinating their interactions to enable adaptive and collaborative reasoning; (3) Collaborative Decision-making: The agent integrates insights from the expert team with accumulated contextual memories, synthesizing them into an evidence-backed diagnostic conclusion. Experiments on various CXR interpretation tasks show that CXRAgent delivers strong performance, providing visual evidence and generalizes well to clinical tasks of different complexity. Code and data are valuable at this link.

Jinhui Lou, Yan Yang, Zhou Yu +4

School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, China · Department of Automation, Tsinghua University, Beijing 100084, China · Department of Colorectal Medical Oncology, Zhejiang Cancer Hospital, Hangzhou, 310022, China +2

Chest X-Ray Classification LLM Agent Orchestration Explainable Medical Image Analysis Multi-Agent Reasoning LLM Agent Planning LLM Agent Reliability

Oct 13, 2025cs.AI

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents

While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking. Unlike execution-based tools (e.g., code or math), whose effects are directly observable, the weak observability of causal dependencies between retrieved evidence and reasoning under format- and outcome-level supervision enables agents to maximize surface-level reward signals without genuinely grounding their reasoning in the returned evidence. This leads to distinctive pathologies, including mode collapse via tool overuse and hallucinated tool usage where tool calls are largely decorative. To address this issue, we propose Proof-of-Use (PoU), an evidence grounded RL framework that explicitly optimizes the causal dependency from retrieval to reasoning and final answers. PoU re-fomulate a fine-grained stepwise interaction protocol in which agents must auditably cite normalized evidence identifiers. We operationalize this via a multi-objective reward design consisting of: (1) two progressive process rewards that constrain citation validity at intermediate steps; (2) a global Answer--Support Alignment reward that enforces consistency between final answers and retrieved evidence; and (3) a curriculum-style adaptive reward mixing mechanism that smoothly transitions agents from dense process supervision to sparse outcome-based objectives. Extensive experiments show the strong performance of PoU and demonstrate the effectiveness in mitigating tool-call hacking. Beyond this, PoU exhibits a notable emergent property: adaptive and robust tool-usage patterns naturally arise under domain and tool shifts, even though PoU does not explicitly optimize for tool adaptation.

Shengjie Ma, Chenlong Deng, Jiaxin Mao +5

Gaoling School of Artificial Intelligence, Renmin University of China China · OPPO China

LLM Agent Reliability RL for Tool Use Evidence-Grounded Reasoning RL for IR

Oct 1, 2025astro-ph.IM

Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data Analysis

We present domain-adapted large language model agents designed to support Cherenkov Telescope Array operation and data analysis. The agents combine contextual knowledge with automated validation and iterative correction to produce more reliable outputs. This approach reduces manual effort, improves consistency, and helps accelerate operational and scientific workflows. The results demonstrate the potential of agentic systems as practical assistants in specialized research environments.

Dmitriy Kostunin, Elisa Jones, Vladimir Sotnikov +3

Deutsches Elektronen-Synchrotron DESY, 15738 Zeuthen, Germany · JetBrains Limited, 8046 Paphos, Cyprus · JetBrains GmbH, 80639 München, Germany +1

High-Energy Physics LLM Agents LLM Agent Reliability Data Analysis Agents

Sep 25, 2025cs.AI

Reasoning or Rambling? Exploring the Effect of Thinking on Agent Persuasion

Understanding persuasion is critical for the safety and reliability of multi-agent systems built on large language models (LLMs). This paper studies persuasion dynamics by contrasting general LLMs with Large Reasoning Models (LRMs) that employ explicit ``thinking'' processes. Through large-scale experiments on objective (MMLU) and subjective (PersuasionBench and Perspectrum) tasks, we identify Persuasion Duality: reasoning enhances an agent's persuasive power while simultaneously increasing its resistance to persuasion. For LRMs, adding thinking content increases persuasion rates by 21 pp on average, yet reduces susceptibility to incorrect persuasion by up to 10 pp on objective tasks. Despite these gains, we uncover a critical vulnerability: persuasiveness often stems from superficial cues such as response length and repetition rather than logical validity. Non-semantic padding or repeated conclusions can match or exceed the persuasive effect of coherent reasoning, revealing a strong length bias in agents' judgments. We further show that persuasion propagates non-linearly in multi-hop agent chains, where intermediate agents may amplify or attenuate influence depending on task subjectivity. Finally, guided by attention analysis, we propose a prompt-level adversarial argument detection method that consistently improves agent robustness.

Haodong Zhao, Jidong Li, Zhaomin Wu +4

School of Computer Science, Shanghai Jiao Tong University · 2National University of Singapore · 3Inner Mongolia Research Institute, Shanghai Jiao Tong University

LLM Agents Persuasion in Language Models LLM Agent Reliability Large Reasoning Models

Aug 29, 2025cs.CL

COCORELI: Enforcing Execution Preconditions for Reliable Collaborative Instruction Following

Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detection alone is insufficient: agents often proceed to execution even after recognizing underspecification, leading to incorrect or unsafe actions. We identify this failure as arising from a lack of coupling between detection and execution, and propose that reliable behavior requires enforcing missing information as a precondition for action. We instantiate this principle in Cocoreli, a modular architecture that represents task structure, tracks missing information, and blocks execution until required details are resolved through targeted clarification. In Cocoreli, detection and prevention are structurally coupled: detecting a missing parameter simultaneously blocks execution. We evaluate Cocoreli in a controlled construction environment isolating underspecification and sequential execution. Cocoreli blocks execution under unresolved specifications by construction, eliminating hallucinated actions. In contrast, chain-of-thought, prompt-chaining, and ReAct-style reasoning may still execute under incomplete specifications despite high detection rates. The same representation supports abstraction and reuse, and generalizes to API workflow tasks on ToolBench. These results show that reliable collaborative execution requires architectural enforcement, not just model capability

Swarnadeep Bhar, Omar Naim, Eleni Metheniti +4

IRIT · ANTI · ENS Paris-Saclay, France +1

Instruction Following LLM Agent Planning LLM Agent Reliability

Aug 20, 2025cs.CL

Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever

Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none is needed or omitting a needed call, can produce unreliable outputs and unnecessary cost. A lightweight remedy is to prepend retrieved examples so LLMs decide tool use in context. However, existing retrievers rank examples by semantic similarity alone. Lexically close or semantically close queries can require opposite behavior, so the retrieved examples may be behaviorally inconsistent and silently mislead the model. We propose Behavior Aligned Retrieval (BAR), a backbone-agnostic training recipe that teaches a dense retriever a behavior-aware similarity, keeping semantically related candidates close only when their tool-use behavior is compatible. BAR does not predict invocation labels; instead, it ranks demonstrations while leaving the final tool-use decision to the LLM. Applied to multiple retrieval backbones, including BERT, Contriever, and Qwen-based representation backbone, BAR consistently improves invocation reliability and reduces unnecessary API calls across 14 LLMs and 3 benchmarks.

Yixin Chen, Ying Xiong, Shangyu Wu +4

City University of Hong Kong · Mohamed Bin Zayed University of Artificial Intelligence · McGill University

In-Context Example Selection In-Context Retrieval Tool-Augmented Language Model Agents LLM Tool Use Tool Selection LLM Agent Reliability+1

Aug 10, 2025cs.AI

EndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis

Endoscopic diagnosis is an iterative process in which clinicians acquire, compare, and verify local visual evidence before reaching a conclusion. Current AI systems do not adequately support this process because fine-grained evidence acquisition and multi-step reasoning remain weakly coupled, complicating reconciliation of image-derived findings with their textual interpretations. This gives rise to two failure modes, hallucinated evidence and uncorrected error accumulation, that undermine diagnostic reliability. We propose EndoCogniAgent, a closed-loop agentic framework that formulates endoscopic diagnosis as a controlled state update process for integrating complementary visual and textual evidence. At each reasoning round, a central planner selects an evidence acquisition action, specialized expert tools extract spatial and semantic observations as structured textual evidence, and a self-consistency validation mechanism examines this evidence along two dimensions, knowledge consistency against the input image and temporal consistency with prior validated findings, before updating the diagnostic state. Validated observations are admitted into the evolving state to condition subsequent planning, while insufficiently supported or conflicting findings are retained with corrective feedback that redirects the planner toward additional verification. We further introduce EndoAgentBench, a workflow-oriented benchmark comprising 6,132 question-answer pairs from 11 endoscopic datasets, to evaluate diagnostic agents across a comprehensive diagnostic chain, from fine-grained visual perception to high-level diagnostic reasoning. EndoCogniAgent achieves 85.23% overall accuracy on perception tasks and 71.13% clinical acceptance rate on reasoning tasks. Blinded clinician evaluation further shows consistent improvements in diagnostic response quality over the evaluated baselines.

Yi Tang, Kai-Ni Wang, Liang-Peng Pu +3

School of Biological Science and Medical Engineering, Southeast University, Nanjing 211189, China · Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University, Nanjing 211189, China · State Key Laboratory of Digital Medical Engineering, Southeast University, Nanjing 211189, China +2

Endoscopy Medical Imaging Medical Diagnosis Agentic Reasoning Clinical Reasoning Medical Image Benchmarks+1

Jul 25, 2025cs.AI

From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls of LLMs in Social Simulation

The integration of Large Language Models (LLMs) into social simulation has generated considerable enthusiasm, but also raises substantial methodological and epistemological challenges. This critical review examines the use of LLMs as cognitive or decision-making components of simulated agents from a computational social science perspective. Rather than treating the psychological evaluation of LLMs as separate from simulation mechanics, we argue that their behavioural and epistemic limitations can become systemic vulnerabilities when scaled to multi-agent societies. We first map the rapidly evolving landscape of LLM-driven platforms, ranging from small narrative sandboxes to population-scale and spatially structured simulations. We then develop a unified critical framework for analyzing the Micro-to-Macro Validity Gap: the propagation and amplification of micro-level limitations, including hallucinations, stochastic inconsistency, representational biases, and alignment effects, into macro-level risks such as the Fluency Fallacy, convergence toward an average persona, and automation bias. We identify contexts in which LLM-based agents offer genuine operational value, including serious games, participatory environments, and exploratory modelling, while distinguishing these uses from confirmatory research and precise social forecasting. Finally, we examine theory-driven hybrid architectures that embed LLMs within explicit, mechanistic, and reproducible Agent-Based Modelling (ABM) frameworks. We argue that such architectures offer a promising but not sufficient path toward improving epistemic control: their validity depends on multi-level evaluation of environmental dynamics, individual behaviour, cross-level interactions, and aggregate outcomes, and they remain vulnerable to the risk of physics washing.

Patrick Taillandier, Jean Daniel Zucker, Arnaud Grignard +4

UR MIAT, University of Toulouse, INRAE, Castanet-Tolosan, France · UMI UMMISCO, IRD, Sorbonne University, Bondy, France · UMR IRIT, University Toulouse Capitole, Toulouse, France +2

Human Behavior Simulation Computational Social Science Agent-Based Modeling Large Language Model-Based Social Simulation LLM Agent Reliability

Jul 21, 2025cs.LG

Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor

Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinations generated by LLMs-where outputs are inconsistent with facts-pose a significant challenge, undermining the credibility of intelligent agents. Only if hallucinations can be mitigated, the intelligent agents can be used in real-world without any catastrophic risk. Therefore, effective detection and mitigation of hallucinations are crucial to ensure the dependability of agents. Unfortunately, the related approaches either depend on white-box access to LLMs or fail to accurately identify hallucinations. To address the challenge posed by hallucinations of intelligent agents, we present HalMit, a novel black-box watchdog framework that models the generalization bound of LLM-empowered agents and thus detect hallucinations without requiring internal knowledge of the LLM's architecture. Specifically, a probabilistic fractal sampling technique is proposed to generate a sufficient number of queries to trigger the incredible responses in parallel, efficiently identifying the generalization bound of the target agent. Experimental evaluations demonstrate that HalMit significantly outperforms existing approaches in hallucination monitoring. Its black-box nature and superior performance make HalMit a promising solution for enhancing the dependability of LLM-powered systems.

Siyuan Liu, Wenjing Liu, Zhiwei Xu +3

College of Computer Science, Nankai University · College of intelligent Science and Technology, Inner Mongolia University of Technology · Institute of Computing Technology, Chinese Academy of Sciences +3

LLM Hallucination Mitigation Hallucination in Language Models AI Agent Monitoring LLM Hallucination Detection LLM Agents LLM Agent Reliability

Jun 14, 2025cs.HC

SheetMind: Actions Set Accuracy, Agents Set the Failure Mode

Spreadsheet agents are converging on elaborate multi-agent designs, yet it is unclear how much of their performance comes from the agents rather than from the action interface they share. We answer this with SheetMind, a Manager-Action-Reflection framework, in a controlled study over all 221 tasks of the SheetCopilot Benchmark: five architectural variants, four backbones, exact McNemar tests on paired outcomes, and a checker reproducing the official chart and pivot comparisons. Replacing the high-level action API with primitive cell operations costs 47.1 points (p < 0.0001) and leaves the agent below a do-nothing baseline, whereas both extra agents together are worth 3.2 points: the Reflection Agent adds +4.5 (p = 0.013), the Manager +1.4 (p = 0.68). Decomposition instead changes how the system fails, cutting silently wrong outputs from 33% to 25% of tasks (p = 0.010). Capability saturates: GPT-5 and the five-times-cheaper GPT-5-mini are not significantly different (61.1% vs. 58.4%, p = 0.15), while GPT-3.5 loses 16.3 points and fails differently. A reflector must judge the step it just took, not the subtask. SheetMind reaches 61.1% Pass@1 with GPT-5 on the full SCB-221, against a do-nothing baseline of 9.0%. Accuracy comes from the operations an agent can name; the agents decide how it fails.

Lyuhao Chen, Xi Cheng, Yanming Kang +11

Carnegie Mellon University · Cornell University · University of California, Berkeley +2

Multi-Agent LLM Systems LLM Agent Evaluation Spreadsheet Automation LLM Agent Reliability

May 26, 2025cs.AI

Shutdownable Agents through POST-Agency

Many fear that future artificial agents will resist shutdown. I present an idea - the POST-Agents Proposal - for ensuring that doesn't happen. I propose that we train agents to satisfy Preferences Only Between Same-Length Trajectories (POST). I then prove that POST - together with other conditions - implies Neutrality+: the agent maximizes expected utility, ignoring the probability distribution over trajectory-lengths. I argue that Neutrality+ keeps agents shutdownable and allows them to be useful.

Elliott Thornley

Agent Reliability AI Agent Safety AI Control LLM Agent Reliability

Aug 23, 2024cs.AI

DrugAgent: Reliable Multi-Agent Integration of Conflicting Biomedical Evidence for Drug-Target Interaction Assessment

Workflows in drug-target interaction (DTI) assessment require integrating heterogeneous data from predictive models, curated resources, and observations from experimental literature. This evidence can be incomplete or conflicting. DrugAgent is a large language model (LLM)-based multi-agent system focused on DTI evidence integration that integrates outputs from machine learning, knowledge graph, and retrieval-augmented generation (RAG) agents. DrugAgent converts agent outputs into interpretable representations, then summarizes conflict across the evidence. We evaluated DrugAgent on kinase screening data of 900 pairs spanning 178 kinases and 42 inhibitors, and an androgen receptor antagonist screening benchmark. On the kinase dataset, LLM-as-a-Judge evaluation indicated outputs were faithful to input evidence in 98.8% of cases. Biological plausibility of returned summarization was high (scores 3-4 out of 5) across ground-truth classes: 79% of Weak activity labels cases (81% for Moderate/77% Strong); Strong cases received higher scores than Weak/Moderate. Label stability showed 98% agreement across runs. Results on the antagonist benchmark were consistent with the kinase dataset. Retrieved literature provided the greatest benefit when direct drug-target evidence was available, highlighting the importance of evidence availability for RAG-based integration. DrugAgent provides heterogeneous evidence-grounded DTI assessment, complementing standalone DTI prediction. We provide strategies to model agreement, conflict, and uncertainty in biomedical evidence integration. Code: https://github.com/sciluna/DrugAgent.

Yoshitaka Inoue, Tianci Song, Xinling Wang +3

Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA · Computational Biology Branch, National Library of Medicine, Bethesda, MD, USA · Khoury College of Computer Sciences, Northeastern University, Arlington, VA, USA +2

Multi-Agent LLM Systems LLM Agent Reliability Drug Discovery

Date pendingcs.CL

GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science

We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agents. GRACE-DS is a set of evaluation metrics in an isolated environment that can be applied to tabular ML tasks specific to a particular organization. It exposes agents to realistic workflow stages, from planning and data inspection through feature engineering, model development, validation, and code repair to final submission, while hidden executable validators measure not only final predictive performance but also leakage avoidance, reproducibility, protocol validity, correction behavior, and reward alignment. The strongest structured regime, flexible iterative interaction (our approach), achieves higher end-to-end normalized hidden-test quality than single-shot generation, unstructured interaction, and restart-based baselines, while also improving protocol-valid completion. Validated across more than 7,000 episodes, these results establish GRACE-DS as a robust platform for assessing the capacity of LLM-based AutoML agents to execute machine learning workflows under production-like conditions and in accordance with organization-specific requirements.

Aleksandr Tsymbalov, Danis Zaripov, Artem Epifanov +1

AI Talent Hub, ITMO University, Saint Petersburg, Russia · HSE University

LLM Agent Evaluation AI Agent Benchmarks Automated Evaluation LLM Agent Reliability