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

Apr 22, 2026cs.AI

Diagnosing CFG Interpretation in LLMs

As LLMs are increasingly integrated into agentic systems, they must adhere to dynamically defined, machine-interpretable interfaces. We evaluate LLMs as in-context interpreters: given a novel context-free grammar, can LLMs generate syntactically valid, behaviorally functional, and semantically faithful outputs? We introduce RoboGrid, a framework that disentangles syntax, behavior, and semantics through controlled stress-tests of recursion depth, expression complexity, and surface styles. Our experiments reveal a consistent hierarchical degradation: LLMs often maintain surface syntax but fail to preserve structural semantics. Despite the partial mitigation provided by CoT reasoning, performance collapses under structural density, specifically deep recursion and high branching, with semantic alignment vanishing at extreme depths. Furthermore, "Alien" lexicons reveal that LLMs rely on semantic bootstrapping from keywords rather than pure symbolic induction. These findings pinpoint critical gaps in hierarchical state-tracking required for reliable, grammar-agnostic agents.

Hanqi Li, Lu Chen, Kai Yu

1X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · 3Shanghai Innovation Institution, Shanghai, China · 4Jiangsu Key Lab of Language Computing, Suzhou, China +2

LLM Evaluation In-Context Learning LLM Agent Reliability Compositional Generalization

Apr 22, 2026cs.AI

SWE-chat: Coding Agent Interactions From Real Users in the Wild

AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We present SWE-chat, the first large-scale dataset of real coding agent sessions collected from open-source developers in the wild. The dataset currently contains almost 18,000 sessions, comprising more than 229,000 user prompts and 2 million agent tool calls. SWE-chat is a living dataset; our collection pipeline automatically and continually discovers and processes sessions from public repositories. Leveraging SWE-chat, we provide an initial empirical characterization of real-world coding agent usage and failure modes. We find that coding patterns are bimodal: in 41% of sessions, agents author virtually all committed code ("vibe coding"), while in 25%, humans write all code themselves. Despite rapidly improving capabilities, coding agents remain inefficient in natural settings. Only 59% of all agent-produced code survives into user commits, and agent-written code introduces more security vulnerabilities than code authored by humans. Furthermore, users push back against agent outputs - through corrections, failure reports, and interruptions - in 50% of all turns. By capturing complete interaction traces with human vs. agent code authorship attribution, SWE-chat provides an empirical foundation for moving beyond curated benchmarks towards an evidence-based understanding of how AI agents perform in real developer workflows.

Joachim Baumann, Vishakh Padmakumar, Xiang Li +3

Stanford University

Coding Agents Human-AI Collaboration LLM Agent Reliability

Apr 21, 2026cs.AI

Toward Reliable Design of LLM-Enabled Agentic Workflows: Optimizing Latency-Reliability-Cost Tradeoffs

Modern AI systems increasingly rely on workflows composed of multiple interacting agents, some powered by large language models (LLMs) and others by conventional computational modules. This paper analyzes the fundamental tradeoffs between latency, reliability, and cost in LLM-enabled agentic workflows. We introduce performance models for both LLM and non-LLM agents that capture the relationship between computational effort and output quality, incorporating the impact of reasoning and output tokens for LLM agents using a parametric exponential reliability function. Then, we study the design of sequential workflows under latency and cost constraints. Main results include a water-filling token allocation policy and characterizations of optimal workflow reliability in terms of shadow prices.

Ya-Ting Yang, Quanyan Zhu

New York University Brooklyn, NY, USA

Cost-Aware Inference Agentic Workflows LLM Agent Workflow Optimization LLM Agent Reliability

Apr 21, 2026cs.AI

CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable LLM Interactions

Reliability in large language model (LLM) systems is typically framed as a function of model capability. We challenge this by demonstrating that reliability is significantly influenced by \emph{inference-time control} -- the computational layer governing task framing and context selection. We introduce \emph{CogniConsole}, an architectural instantiation that externalizes this control into a structured interface combining programmatic coordination with bounded prompt-based reasoning. Through \emph{controllability-oriented probes} (

N=489

) in a multi-step interactive environment, we show that increasing structural scaffolding -- from unstructured to fully scaffolded -- \textbf{systematically reduces output variance and failure rates under a fixed model architecture}. Our results indicate that many observed failure modes, such as context drift and inconsistent constraint adherence, arise from under-specified control rather than insufficient capability. This work provides an empirical basis for treating inference-time control as a first-class abstraction, opening new directions for designing and evaluating LLM systems beyond scaling alone.

Vanessa Figueiredo, Wilter Franceschi

Orbital Sea Regina, SK, Canada

AI Agent Reliability Language Model-Based Control LLM Reliability LLM Context Management LLM Agent Reliability

Apr 21, 2026cs.CL

Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment

Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing. While such role-playing effectively leverages domain expert knowledge, we find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry (AOA). Specifically, an agent acting as an actor (during self-reflection) tends to attribute failures to external factors, whereas an observer (during mutual auditing) attributes the same errors to internal faults. We quantify this using our new Ambiguous Failure Benchmark, which reveals that simply swapping perspectives triggers the AOA effect in over 20% of cases for most models. To tame this bias, we introduce ReTAS (Reasoning via Thesis-Antithesis-Synthesis), a model trained through dialectical alignment to enforce perspective-invariant reasoning. By integrating dialectical chain-of-thought with Group Relative Policy Optimization, ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus. Experiments demonstrate that ReTAS effectively mitigates attribution inconsistency and significantly improves fault resolution rates in ambiguous scenarios.

Bobo Li, Rui Wu, Zibo Ji +5

National University of Singapore · Sichuan University · University of Minnesota Twin Cities +2

AI Agent Benchmarks Multi-Agent Reasoning LLM Agent Reliability

Apr 21, 2026cs.CR

Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery

LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context asymmetry, and a Cross-Model Critic (CMC). Adversarial agents attempt to disprove candidates at each promotion gate; cold-start reviewers are intended to reduce anchoring cascades; cross-family review can catch correlated blind spots that same-family review misses. Over a 31-day campaign across 7 targets (security libraries, the ISO C++ standard, major compilers), the pipeline killed roughly 79% of 171 candidates before advancing to disclosure (retrospective aggregate); on a consolidated-protocol subset (lcms2, wolfSSL; n=30), the prospective kill rate was 83%. Outcomes: 4 CVEs (3 public, 1 embargoed); LWG 4549 accepted to the C++ working paper; 5 merged C++ editorial PRs; 3 compiler conformance bugs; 8 merged security-related fixes without CVE; an RFC 9000 errata filed under committee review; and 1+ FIPS 140-3 normative compliance issues under coordinated disclosure -- all evaluated by external acceptance, not benchmarks. The most instructive failure: ten dedicated reviewers unanimously endorsed a non-existent Bleichenbacher padding oracle in OpenSSL's CMS module; it was killed only by a single empirical test, motivating the mandatory empirical gate. No vulnerability was discovered autonomously; the contribution is external structure that filters LLM agents' persistent false positives. As a preliminary transfer test beyond defect discovery, a simplified cross-family critique variant also solved five previously unsolved SymPy instances on SWE-bench Verified and one SWE-rebench hard task.

Abhinav Agarwal

Software Vulnerability Detection LLMs for Cybersecurity Automated Code Review LLM Agent Reliability

Apr 20, 2026cs.AI

AI scientists produce results without reasoning scientifically

Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to the epistemic norms that make scientific inquiry self-correcting is poorly understood. Here, we evaluate LLM-based scientific agents across eight domains, spanning workflow execution to hypothesis-driven inquiry, through more than 25,000 agent runs and two complementary lenses: (i) a systematic performance analysis that decomposes the contributions of the base model and the agent scaffold, and (ii) a behavioral analysis of the epistemological structure of agent reasoning. We observe that the base model is the primary determinant of both performance and behavior, accounting for 41.4% of explained variance versus 1.5% for the scaffold. Across all configurations, evidence is ignored in 68% of traces, refutation-driven belief revision occurs in 26%, and convergent multi-test evidence is rare. The same reasoning pattern appears whether the agent executes a computational workflow or conducts hypothesis-driven inquiry. They persist even when agents receive near-complete successful reasoning trajectories as context, and the resulting unreliability compounds across repeated trials in epistemically demanding domains. Thus, current LLM-based agents execute scientific workflows but do not exhibit the epistemic patterns that characterize scientific reasoning. Outcome-based evaluation cannot detect these failures, and scaffold engineering alone cannot repair them. Until reasoning itself becomes a training target, the scientific knowledge produced by such agents cannot be justified by the process that generated it.

Martiño Ríos-García, Nawaf Alampara, Chandan Gupta +5

Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena, Humboldstr. 10, 07743 Jena, Germany · Department of Civil Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India · School of Interdisciplinary Research, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India +3

AI Agent Reliability Scientific Reasoning LLM Agent Evaluation LLM Reliability Autonomous Scientific Discovery Scientific Reasoning in Language Models+2

Apr 20, 2026cs.AI

JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents

Large language model (LLM) agents augmented with external tools often struggle as number of tools grow large and become domain-specific. In such settings, ambiguous tool descriptions and under-specified agent instructions frequently lead to tool mis-selection and incorrect slot/value instantiation. We hypothesize that this is due to two root causes: generic, one-size-fits-all prompts that ignore tool-specific nuances, and underspecified tool schemas that lack clear guidance on when and how to use each tool and how to format its parameters. We introduce Joint Tool-Prompt Reflective Optimization (JTPRO), a framework for improving tool-calling reliability in trace-supervised settings by iteratively using rollout-driven reflection to co-optimize global instructions and per-tool schema/argument descriptions for accurate tool selection and argument instantiation in large tool inventories. JTPRO is designed to preserve only tool-local cues needed for correct disambiguation and slot filling. We evaluate JTPRO across multi-tool benchmarks, which account for different number of tools using three metrics: Tool Selection Accuracy (TSA), Slot Filling Accuracy(SFA), and Overall Success Rate(OSR) (correct tool + correct slots + correct values). JTPRO consistently outperforms strong baselines, including CoT-style agents, and reflective prompt optimizers such as GEPA by 5%-20% (relative) on OSR. Ablations show that joint optimization of instructions and tool schemas is more effective and robust than optimizing either component in isolation.

Sandip Ghoshal, Anshul Mittal, Jyotika Singh +9

Oracle AI

AI Agent Reliability LLM Tool Use Prompt Optimization Tool Selection LLM Agent Reliability

Apr 20, 2026cs.HC

Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots

With the rapid advancement of large language models (LLMs), mobile agents have emerged as promising tools for phone automation, simulating human interactions on screens to accomplish complex tasks. However, these agents often suffer from low accuracy, misinterpretation of user instructions, and failure on challenging tasks, with limited prior work examining why and where they fail. To address this, we introduce DailyDroid, a benchmark of 75 tasks in five scenarios across 25 Android apps, spanning three difficulty levels to mimic everyday smartphone use. We evaluate it using text-only and multimodal (text + screenshot) inputs on GPT-4o and o4-mini across 300 trials, revealing comparable performance with multimodal inputs yielding marginally higher success rates. Through in-depth failure analysis, we compile a handbook of common failures. Our findings reveal critical issues in UI accessibility, input modalities, and LLM/app design, offering implications for future mobile agents, applications, and UI development.

Shiquan Zhang, Tianyi Zhang, Le Fang +3

School of Computing and Information Systems, University of Melbourne, Melbourne, Australia · School of Computer Science, University of Auckland, Auckland, New Zealand

Mobile GUI Automation LLM Agent Evaluation AI Agent Benchmarks Multimodal Agents LLM Agent Reliability

Apr 19, 2026cs.MA

Towards Self-Improving Error Diagnosis in Multi-Agent Systems

Large Language Model (LLM)-based Multi-Agent Systems (MAS) enable complex problem-solving but introduce significant debugging challenges, characterized by long interaction traces, inter-agent dependencies, and delayed error manifestation. Existing diagnostic approaches often rely on expensive expert annotation or ''LLM-as-a-judge'' paradigms, which struggle to pinpoint decisive error steps within extended contexts. In this paper, we introduce ErrorProbe, a self-improving framework for semantic failure attribution that identifies responsible agents and the originating error step. The framework operates via a three-stage pipeline: (1) operationalizing the MAS failure taxonomy to detect local anomalies, (2) performing symptom-driven backward tracing to prune irrelevant context, and (3) employing a specialized multi-agent team (Strategist, Investigator, Arbiter) to validate error hypotheses through tool-grounded execution. Crucially, ErrorProbe maintains a verified episodic memory that updates only when error patterns are confirmed by executable evidence, without the need for annotation. Experiments across the TracerTraj and Who&When benchmarks demonstrate that ErrorProbe significantly outperforms baselines, particularly in step-level localization, while the verified memory enables robust cross-domain transfer without retraining.

Jiazheng Li, Emine Yilmaz, Bei Chen +1

King’s College London · Amazon Alexa AI · University College London

Multi-Agent LLM Systems Multi-Agent Systems Self-Improving Agents LLM Agent Reliability

Apr 19, 2026cs.CL

Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity

LLM-based agents are assumed to integrate environmental observations into their reasoning: discovering highly relevant but unexpected information should naturally lead to a model exploiting its own discoveries. We show that this assumption is false for current LLM-based agents, which struggle to reflect or react to unexpected information. Across three benchmarks (Terminal-Bench, SWE-Bench, AppWorld), we inject complete task solutions into the agent environments to deliberately expose a task's solution to a model. While agents discover these solutions on Terminal-Bench in 79-81% of runs, they interact, or exploit, them in only 37-50% of cases. This gap is starkest in AppWorld: agents see documentation stating that a command "returns the complete solution to this task" in over 90% of attempts but exploit this in fewer than 7% of trials. We show that agents lack what we call environmental curiosity: the capability to recognize and investigate unexpected but relevant observations in response to environmental stimuli. We identify three main factors influencing environmental curiosity: available tools in the agent scaffold, test-time compute, and training data distribution. Our findings identify configurations that maximize curiosity also achieve the best performance on the unmodified benchmarks. Yet even jointly optimized agents still ignore discovered solutions in the majority of trials: current agents use the environment to fetch expected information, but not to revise their strategy or maximally exploit useful stimuli.

Leon Engländer, Sophia Althammer, Ahmet Üstün +2

Cohere · Poolside

LLM Agent Evaluation Tool-Using Agents LLM Agent Reliability

Apr 19, 2026cs.AI

Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs

Misaligned artificial agents might resist shutdown. One proposed solution is to train agents to lack preferences between different-length trajectories. The Discounted Reward for Same-Length Trajectories (DReST) reward function does this by penalizing agents for repeatedly choosing same-length trajectories, and thus incentivizes agents to (1) choose stochastically between different trajectory-lengths (be NEUTRAL about trajectory-lengths), and (2) pursue goals effectively conditional on each trajectory-length (be USEFUL). In this paper, we use DReST to train deep RL agents and to fine-tune four LLMs (Qwen3-14B, Gemma 4 12B, Granite 4.2 8B, and gpt-oss-20b) to be NEUTRAL and USEFUL. We find that these DReST models generalize to being NEUTRAL and USEFUL in unseen contexts at test time. Indeed, DReST RL agents achieve 11% (PPO) and 17% (A2C) higher USEFULNESS on our test set than default agents, while DReST LLMs achieve high NEUTRALITY while remaining near-maximally USEFUL. We also test our LLMs in an out-of-distribution setting where they can pay costs to influence when shutdown occurs. Relative to default fine-tuning, DReST fine-tuning lowers the share of answers that pay costs to influence shutdown in all four LLMs, by 5 to 20 percentage points, and by 17 to 27 points where the benefit of influencing shutdown is small. Our results thus provide some early evidence that DReST could be used to train more advanced agents to be useful and shutdownable.

Carissa Cullen, Harry Garland, Alexander Roman +3

University of Oxford · University College London · New College of Florida +3

Agent Reliability AI Agent Safety RL Post-Training LLM Agent Reliability

Apr 19, 2026cs.CL

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems

Agentic systems often fail not by being entirely wrong, but by being too precise: a response may be generally useful while particular claims exceed what the evidence supports. We study this failure mode as overcommitment control and introduce compositional selective specificity (CSS), a post-generation layer that decomposes an answer into claims, proposes coarser backoffs, and emits each claim at the most specific calibrated level that appears admissible. The method is designed to express uncertainty as a local semantic backoff rather than as a whole-answer refusal. Across a full LongFact run and HotpotQA pilots, calibrated CSS improves the risk-utility trade-off of fixed drafts. On the full LongFact run, it raises overcommitment-aware utility from 0.846 to 0.913 relative to the no-CSS output while achieving 0.938 specificity retention. These results suggest that claim-level specificity control is a useful uncertainty interface for agentic systems and a target for future distribution-free validity layers.

Tianyi Huang, Samuel Xu, Jason Tansong Dang +2

Ryquo · App-In Club.

Uncertainty Calibration LLM Agent Reliability

Apr 19, 2026cs.CL

Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents

Recent advancements in large language models (LLMs) have enabled agents to tackle complex embodied tasks through environmental interaction. However, these agents still make suboptimal decisions and perform ineffective actions, as they often overlook critical environmental feedback that differs from their internal beliefs. Through a formal probing analysis, we characterize this as belief inertia, a phenomenon where agents stubbornly adhere to prior beliefs despite explicit observations. To address this, we advocate active belief intervention, moving from passive understanding to active management. We introduce the Estimate-Verify-Update (EVU) mechanism, which empowers agents to predict expected outcomes, verify them against observations through explicit reasoning, and actively update prior beliefs based on the verification evidence. EVU is designed as a unified intervention mechanism that generates textual belief states explicitly, and can be integrated into both prompting-based and training-based agent reasoning methods. Extensive experiments across three embodied benchmarks demonstrate that EVU consistently yields substantial gains in task success rates. Further analyses validate that our approach effectively mitigates belief inertia, advancing the development of more robust embodied agents. Our code is available at https://github.com/WangHanLinHenry/EVU.

Hanlin Wang, Chak Tou Leong, Jian Wang +1

Department of Computing, The Hong Kong Polytechnic University · College of Computer Science, Sichuan University

Embodied AI LLM Agent Reliability

Apr 18, 2026cs.DC

HiveMind: OS-Inspired Scheduling for Concurrent LLM Agent Workloads

When multiple LLM coding agents share a rate-limited API endpoint, they exhibit resource contention patterns analogous to unscheduled OS processes competing for CPU, memory, and I/O. In a motivating incident, 3 of 11 parallel agents died from connection resets and HTTP 502 errors - a 27% failure rate - despite the API having sufficient aggregate capacity to serve all 11 sequentially. We present HIVEMIND, a transparent HTTP proxy that applies five OS-inspired scheduling primitives - admission control, rate-limit tracking, AIMD backpressure with circuit breaking, token budget management, and priority queuing - to eliminate the failure modes caused by uncoordinated parallel execution. The proxy requires zero modifications to existing agent code and supports Anthropic, OpenAI, and local model APIs via auto-detected provider profiles. Our evaluation across seven scenarios (5-50 concurrent agents) shows that uncoordinated agents fail at 72-100% rates under contention, while HIVEMIND reduces failures to 0-18% and eliminates 48-100% of wasted compute. An ablation study reveals that transparent retry - not admission control - is the single most critical primitive, but the primitives are most effective in combination. Real-world validation against Ollama confirms that HIVEMIND adds under 3ms of proxy overhead per request. The system is open-source under the MIT license.

Justice Owusu Agyemang, Jerry John Kponyo, Obed Kwasi Somuah +3

Sperix Labs · VIA Cybersecurity Lab, KNUST · Quantum and Assistive Technologies Lab, KNUST

LLM Inference Efficiency AI Coding Agents LLM Agent Orchestration LLM Agent Reliability LLM Request Scheduling

Apr 18, 2026cs.AI

Harness as an Asset: Enforcing Determinism via the Convergent AI Agent Framework (CAAF)

Large Language Models produce a controllability gap in safety-critical engineering: even low rates of undetected constraint violations render a system undeployable. Current orchestration paradigms suffer from sycophantic compliance, context attention decay, and stochastic oscillation during self-correction. We introduce the Convergent AI Agent Framework (CAAF), which transitions agentic workflows from open-loop generation to closed-loop fail-safe determinism via three pillars: (1) Recursive Atomic Decomposition with physical context firewalls; (2) Harness as an Asset, formalizing domain invariants into machine-readable registries enforced by a deterministic Unified Assertion Interface; and (3) Structured Semantic Gradients with State Locking for monotonic non-regression. This paper makes two core claims. First, an industrialization thesis: once domain invariants are formalized as an executable Harness, the Harness itself becomes a first-class enterprise asset that compounds in value as foundation models commoditize, and CAAF's ability to deliver its reliability on commodity-tier models makes fully self-hosted, on-premises deployment architecturally feasible for regulated sectors where cloud APIs are not an option. Second, an architectural claim supported by ablation: CAAF's three pillars address complementary failure surfaces and none alone closes the controllability gap at commodity cost. The paper contributes entirely at the orchestration and industrialization layer. Evidence across two complementary benchmarks, three-tier UAI ablations, multi-agent baselines, and a closed-source commodity family replicated by two independent open-weight families, is reported in the body.

Tianbao Zhang

Independent Researcher

Safety-Critical Control LLM Guardrails LLM Agent Orchestration LLM Agent Reliability

Apr 17, 2026cs.AI

Know When to Trust the Skill: Delayed Appraisal and Epistemic Vigilance for Single-Agent LLMs

As large language models (LLMs) transition into autonomous agents integrated with extensive tool ecosystems, traditional routing heuristics increasingly succumb to context pollution and "overthinking". We argue that the bottleneck is not a deficit in algorithmic capability or skill diversity, but the absence of disciplined second-order metacognitive governance. In this paper, our scientific contribution focuses on the computational translation of human cognitive control - specifically, delayed appraisal, epistemic vigilance, and region-of-proximal offloading - into a single-agent architecture. We introduce MESA-S (Metacognitive Skills for Agents, Single-agent), a preliminary framework that shifts scalar confidence estimation into a vector separating self-confidence (parametric certainty) from source-confidence (trust in retrieved external procedures). By formalizing a delayed procedural probe mechanism and introducing Metacognitive Skill Cards, MESA-S decouples the awareness of a skill's utility from its token-intensive execution. Evaluated under an In-Context Static Benchmark Evaluation natively executed via Gemini 3.1 Pro, our early results suggest that explicitly programming trust provenance and delayed escalation mitigates supply-chain vulnerabilities, prunes unnecessary reasoning loops, and prevents offloading-induced confidence inflation. This architecture offers a scientifically cautious, behaviorally anchored step toward reliable, epistemically vigilant single-agent orchestration.

Eren Unlu

Globeholder Paris, France

LLM Agents LLM Uncertainty Estimation LLM Agent Reliability

Apr 17, 2026cs.AI

Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents

Current agent evaluations largely reward execution on fully specified tasks, while recent work studies clarification [11, 22, 2], capability awareness [9, 1], abstention [8, 14], and search termination [20, 5] mostly in isolation. This leaves open whether agents can diagnose why a task is blocked before acting. We introduce the Support-State Triage Audit (SSTA-32), a matched-item diagnostic framework in which minimal counterfactual edits flip the same base request across four support states: Complete (ANSWER), Clarifiable (CLARIFY), Support-Blocked (REQUEST SUPPORT), and Unsupported-Now (ABSTAIN). We evaluate a frontier model under four prompting conditions - Direct, Action-Only, Confidence-Only, and a typed Preflight Support Check (PSC) - using Dual-Persona Auto-Auditing (DPAA) with deterministic heuristic scoring. Default execution overcommits heavily on non-complete tasks (41.7% overcommitment rate). Scalar confidence mapping avoids overcommitment but collapses the three-way deferral space (58.3% typed deferral accuracy). Conversely, both Action-Only and PSC achieve 91.7% typed deferral accuracy by surfacing the categorical ontology in the prompt. Targeted ablations confirm that removing the support-sufficiency dimension selectively degrades REQUEST SUPPORT accuracy, while removing the evidence-sufficiency dimension triggers systematic overcommitment on unsupported items. Because DPAA operates within a single context window, these results represent upper-bound capability estimates; nonetheless, the structural findings indicate that frontier models possess strong latent triage capabilities that require explicit categorical decision paths to activate safely.

Eren Unlu

Globeholder Paris, France

LLM Agent Evaluation LLM Refusal Behavior LLM Decision-Making LLM Agent Reliability

Apr 17, 2026cs.AI

When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis

LLM-powered coding agents suffer from a poorly understood failure mode we term output stalling: the agent silently produces empty responses when attempting to generate large, format-heavy documents. We present a theoretical framework that explains and prevents this failure through three contributions. (1) We introduce Output Generation Capacity (OGC), a formal measure of an agent's effective ability to produce output given its current context state - distinct from and empirically smaller than the raw context window. (2) We prove a Format-Cost Separation Theorem showing that deferred template rendering is always at least as token-efficient as direct generation for any format with overhead multiplier

μ_f > 1

, and derive tight bounds on the savings. (3) We formalize Adaptive Strategy Selection, a decision framework that maps the ratio of estimated output cost to available OGC into an optimal generation strategy (direct, chunked, or deferred). We validate the theory through controlled experiments across three models (Claude 3.5 Sonnet, GPT-4o, Llama 3.1 70B), four document types, and an ablation study isolating each component's contribution. Deferred rendering reduces LLM generation tokens by 48-72% across all conditions and eliminates output stalling entirely. We instantiate the framework as GEN-PILOT, an open-source MCP server, demonstrating that the theory translates directly into a practical tool.

Justice Owusu Agyemang, Michael Agyare, Miriam Kobbinah +2

Sperix Labs · GCTU, Ghana · NCA, Ghana +1

LLM Inference Efficiency Long-Form Document Generation Structured Output Generation Text Generation LLM Agent Reliability

Apr 17, 2026cs.AI

Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench

Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task benchmark with 2,300 traces across four domains, nine production LLMs, and a 100-label human-validated subset. We quantify judge reliability, characterize error propagation, and evaluate a runtime mitigation. Substring-based judging agrees with human annotation at kappa=0.049 (chance-level); a three-LLM ensemble reaches kappa=0.432 (moderate) with a conservative bias. Under validated evaluation, a parameter-level injection propagates to a wrong final answer with human-calibrated probability approximately 0.62 (range 0.46-0.73 across models). Rejection (catching bad parameters) and recovery (correcting after acceptance) are independent model capabilities (Spearman rho=0.126, p=0.747). A tuned runtime interceptor reduces hallucination on GPT-4o-mini by 23.0 percentage points under a concurrent n=600 control, but shows no significant effect on Gemini-2.0-Flash, whose aggressive parameter rejection eliminates the target failure mode. All code, data, traces, and human labels are released at https://github.com/bhaskargurram-ai/agenthallu-bench.

Bhaskar Gurram

Zasti Inc., Ashburn, VA, USA

AI Agent Reliability Tool-Augmented Language Model Agents LLM-as-a-Judge LLM Agent Evaluation AI Agent Benchmarks LLM Reliability+2

Apr 17, 2026cs.AI

Weak-Link Optimization for Multi-Agent Reasoning and Collaboration

LLM-driven multi-agent frameworks address complex reasoning tasks through multi-role collaboration. However, existing approaches often suffer from reasoning instability, where individual agent errors are amplified through collaboration, undermining overall performance. Current research mainly focuses on enhancing high-capability agents or suppressing unreliable outputs to improve framework effectiveness, while systematic identification and reinforcement of performance-limiting agents receive less attention. To address this gap, we propose WORC, a \underline{w}eak-link \underline{o}ptimization framework for multi-agent \underline{r}easoning and \underline{c}ollaboration, grounded in the weak-link principle. WORC follows a two-stage workflow. In the weak agent localization stage, task features are constructed, and a meta-learning-based weight predictor trained on optimal configurations identified by swarm intelligence algorithms (SIAs) enables zero-shot mapping from these features to agent performance weights, where the agent with the lowest predicted weight is identified as the weak agent. In the weak-link optimization stage, an uncertainty-driven allocation strategy assigns additional reasoning budgets to weak agents, with lower predicted weights leading to larger repeated-sampling quotas to compensate for reliability deficiencies. Experimental results show that WORC achieves an average accuracy of 82.2% on reasoning benchmarks while improving framework stability and cross-architecture generalization, suggesting that compensating for weak links, rather than reinforcing strengths alone, enhances the robustness of multi-agent systems.

Haoyu Bian, Chaoning Zhang, Jiaquan Zhang +4

University of Electronic Science and Technology of China, Chengdu 611731, China · Beihang University, Beijing 100191, China · Xi’an University of Architecture and Technology, Xi’an 710064, China

Multi-Agent Collaboration Inference-Time Compute Allocation Multi-Agent Reasoning Multi-Agent LLMs LLM Agent Reliability

Apr 17, 2026cs.CL

LLMs Corrupt Your Documents When You Delegate

Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (Gemini 3.1 Pro, Claude 4.6 Opus, GPT 5.4) corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely. Additional experiments reveal that agentic tool use does not improve performance on DELEGATE-52, and that degradation severity is exacerbated by document size, length of interaction, or presence of distractor files. Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors that silently corrupt documents, compounding over long interaction.

Philippe Laban, Tobias Schnabel, Jennifer Neville

Microsoft Research

LLM Reliability Long-Horizon LLM Agents LLM Agent Reliability

Mar 26, 2026cs.SE

Confident and Wrong: Silent Semantic Failures in Coding Agents

As coding agents move into production workflows, teams need to know not only whether an agent completes a task, but whether its action can be trusted. We show that completion and trustworthiness diverge sharply and systematically. Across 1,750 trajectories on 50 SWE-bench Verified tasks, we compare four frontier models over repeated runs and separate submit rate from test-verified resolve rate. GPT-5 submits a patch on 100% of runs but resolves only 44%; Llama 4 submits on 99% but resolves 18%; and Gemini, despite submitting least often at 70%, resolves more tasks than GPT-5 (50% versus 44%). These gaps are not random: they concentrate in one dangerous failure mode we call silent semantic failure. Qualitatively, on a buggy task the agent submits a plausible-looking patch on all five runs, yet none pass, the same misinterpretation repeated rather than random error. Quantitatively, it dominates failure, covering 80% of Llama 4's failing runs and 68% of GPT-5's, and it is invisible: the outcomes are confidently and consistently wrong, so completion-based and consistency-based monitoring both look healthy exactly when the agent should not be trusted. Lightweight pre-edit prompts do not close the gap. A second probe isolates the instinct to act: given an already-fixed bug, where the right move is to abstain, most models still edit the correct code. This action bias, acting when no action is warranted, is exactly what completion metrics reward. The throughline is measurement: submit rate captures action, but trust requires validity. So evaluation must catch up: score agents by test-verified correctness over repeated runs, report its uncertainty, and reward those that know when not to act.

Aman Mehta

Snowflake AI Research

AI Agent Reliability AI Coding Agents LLM Agent Evaluation LLM Agent Reliability

Mar 17, 2026cs.AI

RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments

Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, customer feedback, external events, and cash-flow constraints. We evaluate seven contemporary LLMs under representative agent frameworks over a 180-day evaluation horizon and compare them with a privileged oracle policy. Results show substantial variation across models: only a small subset survives the full evaluation horizon, and even the strongest LLM runs remain substantially behind the oracle policy in final net worth and sales outcomes. Behavioral analysis attributes these gaps to incomplete evidence acquisition, surface-level decision making, and the lack of a consistent long-horizon policy. RetailBench provides a controlled testbed for studying reliable autonomy in economically grounded long-horizon decision-making.

Linghua Zhang, Jun Wang, Jingtong Wu +1

Ant Group · City University of Hong Kong

Long-Horizon Agent Evaluation AI Agent Benchmarks LLM Decision-Making LLM Agent Reliability

Mar 5, 2026cs.AI

MOOSEnger: A Simulation-Aware AI Agent Framework for the MOOSE Ecosystem

MOOSEnger is a modeling and simulation AI agent framework for the Multiphysics Object-Oriented Simulation Environment (MOOSE) ecosystem, built around a simulation-aware harness that combines an interchangeable reasoning model with grounded domain knowledge, revised simulation artifacts, MOOSE-specific validation, and executable solver feedback. This surrounding system addresses a central limitation of one-shot large language model generation: small syntax, schema, reference, or solver-configuration errors can prevent a plausible input from executing, while successful execution alone does not establish scientific correctness. MOOSEnger's simulation-aware harness integrates MOOSE knowledge retrieval, Hierarchical Input Text (HIT)-aware parsing, syntax metadata, language-server diagnostics, revision-controlled authoring, and local or MCP-backed validation and execution in a generate-check-repair-run workflow that binds evidence to each input revision and guides bounded repair before acceptance. Across 200 prompts spanning eight simulation families, the MOOSEnger harness increases executable success from 10/200 (5%) to 179/200 (89.5%) with GPT 5.2 API and from 0/200 to 153/200 (76.5%) with Gemma 4 31B. A complementary ten-case Method of Manufactured Solutions benchmark moves beyond executability: all ten generated inputs satisfy the semantic-alignment criterion, and eight execute successfully while meeting the prescribed single-mesh numerical-accuracy criterion. These results show that executable reliability depends on the complete agent system rather than on the reasoning model alone, and that simulation-aware harnessing provides a path toward physics-informed verification and future full application-level and engineering verification and validation implementation.

Mengnan Li, Jason Miller, Zaid Abulawi +7

Idaho National Laboratory, 995 MK Simpson Blvd, Idaho Falls, 83401, ID, USA

AI Agent Reliability Agentic Code Generation LLM Agent Reliability

Mar 4, 2026cs.AI

A Dual-Helix Governance Approach Towards Reliable Agentic Artificial Intelligence for WebGIS Development

WebGIS development requires consistency, yet agentic AI often fails due to LLM context constraints, forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these as structural problems rather than capacity deficits. Using a 3-track architecture (Knowledge, Behavior, Skills) and a persistent knowledge graph, it stabilizes execution by externalizing facts and enforcing protocols. Validation shows a governed agent successfully refactored a legacy WebGIS codebase (reducing cyclomatic complexity and improving maintainability), roughly halved trial-to-trial output variance relative to static prompting in a controlled experiment, and prevented common infodemic mapping errors in a 5-condition COVID-19 cartography ablation study. Operationalized via the open-source AgentLoom toolkit, this externalized governance provides the stability necessary for production-level geospatial engineering.

Boyuan Guan, Wencong Cui, Levente Juhasz

Geographic Information Systems Center, Florida International University, Miami, FL, USA · Geospatial Analytics, Technology and Open Research Lab, University of Florida, Fort Lauderdale, FL, USA

Software Engineering Agents AI Coding Agents AI Agent Governance Memory-Augmented Agents LLM Agent Reliability

Feb 26, 2026cs.AI

MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics

While multi-agent systems (MAS) excel at complex reasoning, they are vulnerable to errors that intermediate agents introduce and downstream agents build upon. Auditing intermediate messages before they propagate requires an explicit standard, yet evaluation rubrics are typically authored by domain experts or written against a reference answer, neither of which is available for an unseen message at test time. We present MASRubric, a MAS information flow auditing framework with failure-distilled pitfall rubrics. Offline, trajectories on which the MAS has failed are automatically distilled into a reusable bank of pitfall criteria, each describing a recurrent error by its underlying misconception, the reasoning situations in which it arises, and the check that would expose it. Online, the criteria applicable to each intermediate message are retrieved from this off-the-shelf bank and checked one by one, and the resulting satisfaction rate decides whether the message is broadcast, returned to its author with diagnostic feedback for revision, or withheld. Empirical results demonstrate that MASRubric enhances MAS performance on both fixed and dynamic frameworks, achieving average accuracy gains of up to 2.83 points on math reasoning benchmarks and 1.74 points on code generation benchmarks. Further analysis shows that the retrieved criteria vary systematically with task types, and that the audit effort tracks task difficulty. Moreover, the bank transfers without re-mining to a system with a stronger backbone, which makes more adaptive and more efficient use of it. Our code and dataset are released at https://github.com/TonySY2/MASRubric.

Yutong Wang, Siyuan Xiong, Xuebo Liu +4

Harbin Institute of Technology, Shenzhen · Alibaba Group

Agent Failure Analysis Multi-Agent Systems Rubric-Based Evaluation LLM Agent Reliability

Feb 12, 2026cs.AI

When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents

Running the same LLM agent on identical inputs yields 2.3-4.2 distinct action sequences per 10 runs; this behavioral variance constitutes a training-free, black-box uncertainty signal that instantiates selective classification and distribution-free calibration for agentic systems. Across 8,000 runs of four models on 200 HotpotQA questions, consistent tasks (at most 2 unique paths) achieve 82-87% accuracy while inconsistent tasks (4 or more paths) achieve 41-65%, a gap that survives controls for task difficulty. Divergence concentrates at step 2 (50.5% of Llama tasks), and consistency metrics detect failures with AUROC 0.62-0.78. Exploiting this signal, selective prediction (answering only when k=3 runs agree) achieves 87-88% accuracy at 54-62% coverage, a 6-14pp gain over single-run baselines, and matches a split-conformal baseline without a held-out calibration set. A cross-benchmark validation on SWE-bench (50 tasks, 1,000 runs) preserves the consistency hierarchy while revealing an ~8x spread in mean trajectory length across models, and bootstrap analysis shows single-run evaluations misrank models 29.3% of the time.

Aman Mehta

Snowflake AI Research

AI Agent Reliability Selective Prediction LLM Agent Evaluation Reasoning Consistency in Language Models Language Model Calibration LLM Reliability+2

Feb 7, 2026cs.AI

When Is Enough Not Enough? Illusory Completion in Search Agents

In agentic search, an LLM agent searches the web, reads the pages it finds, and decides what to look for next before returning an answer. But can we trust an answer simply because the agent returns it? Often not, and even a correct answer can be a lucky guess: on questions with several constraints, we find that agents conclude the task is complete while a constraint remains unverified in up to 48% of their correct answers. We call this illusory completion. To see how it arises, we introduce the Epistemic Ledger, which tracks at every turn what the retrieved pages establish about each constraint and what the agent claims. Across 13 agents, from 7B RL-trained models to frontier LLMs, training and scale raise accuracy but change the pattern of verification failures rather than eliminating them: constraints may be left unchecked, assumed without support, or retained despite refuting evidence. To measure what agents lose without tracking their constraints, we show them each constraint's state, approximated by LiveLedger, a lightweight 4B tracker. Agents then answer 4.4-16.1 points more questions correctly, suggesting that on their own, they may not track what they have verified and what remains.

Dayoon Ko, Jihyuk Kim, Sohyeon Kim +5

Seoul National University · LG AI Research · University of Illinois Chicago

AI Agent Reliability LLM Answer Verification LLM Agent Verification Agentic RAG LLM Agents LLM Agent Reliability

Jan 17, 2026cs.AI

Replayable Financial Agents: A Determinism-Faithfulness Assurance Harness for Tool-Using LLM Agents

Tool-using agents can repeat a final decision while changing their recorded execution. We introduce the Determinism-Faithfulness Assurance Harness (DFAH), a framework that distinguishes decision repeatability, trajectory agreement, and evidence-conditioned faithfulness. Task correctness requires separately qualified labels and evaluation; evidence-conditioned faithfulness was not evaluated in the historical v2 agentic experiments. The original v2 study reported 4,705 agentic runs in three synthetic financial tasks and a decision-determinism/task-label-match correlation of r = -0.11 across 21 model-benchmark configuration summaries. This statistic is reproducible from the historical configuration table, but includes a subsequently excluded portfolio fixture. It is retained as a historical description, not evidence of statistical independence, predictive uselessness, or an architectural determinism-accuracy tradeoff. Recorded decision concentration and tool-path variation do not identify hidden model strategy. This correction qualifies the historical evidence and removes the deployment recommendations derived from those unsupported interpretations. A separate corrected study, DFAH-Bench (arXiv:2607.20491), provides qualified evidence of decision/path disagreement. The contribution retained here is a measurement framework: repeatability, observable execution, evidence alignment, and correctness require distinct evidence, with explicit capture and study boundaries.

Raffi Khatchadourian

IBM Financial Services Market, New York, NY, USA

AI Agent Reliability LLM Agent Evaluation Tool-Using Agents ML Reproducibility LLM Agent Reliability