Agent Failure Analysis

Ask about this topic

Overview

Agent failure analysis examines how errors arise and spread in tool-using, coding, GUI, and multi-agent systems, including failures hidden by apparently successful final outcomes. Common approaches annotate execution trajectories, classify failure modes, monitor runtime behavior, and use dependency graphs or counterfactual replay to distinguish root causes from downstream symptoms. Benchmarks use real or human-labeled traces, controlled fault injection, and repeated runs to test diagnosis and recovery. A central challenge is making attributions genuinely causal and robust when logs are incomplete, task conditions vary, and benchmark shortcuts can make performance look stronger than it is.

Latest papers

CardsList

154 papers27 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

Sep 26, 2026

DAAF: From Failure Localization to Editable System Assets in LLM Agents

Deployed LLM agents increasingly rely on persistent, versioned system assets such as routing rules, knowledge segments, prompt instructions, and reusable skills. Failure-localization methods can identify where an error manifests in an agent or execution trace, but repair requires a different decision: which editable system asset should be changed, and is that change expected to improve the task outcome? We study this gap through component-attribute failure attribution, where diagnosis targets versioned, addressable items rather than execution locations. We propose the Detection-Aware Attribution Framework (DAAF), which learns the effects of valid attribute replacements and amortizes this intervention evidence into deployment-time diagnosis. DAAF combines sparse and noisy failure signals to decide whether intervention is warranted, learns component-type-conditioned replacement effects from controlled replays evaluated by executable task outcomes, and shares supervision across requests with compatible intervention responses. At diagnosis time, DAAF uses only the observed execution, registered candidates, and available failure signals; it requires neither counterfactual replay nor task reward and returns no_change, a repair target, or an unresolved decision when evidence is insufficient. On held-out tau^2-bench Telecom tasks, DAAF achieves 80.72% attribute Hit@1, recovers 62.65% of failed executions while limiting clean-task regression to 3.23%, and reaches 71.93% overall task success. These results show that intervention-grounded attribute attribution can connect failure localization to executable system repair.

Xiaoyang Yuan, Qi Liu, Yubin Ruan +9

Tencent

Failure Attribution for LLM AgentsAgent Failure AnalysisLLM Agent Reliability
AskPDF
Sep 23, 2026

Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents

Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution evidence. Success rates alone obscure inefficiency, adaptation through retries, and recognition of success or failure. We present an end-to-end diagnostic study of an Autonomous Adversary system with orchestrator, executor, and validator LLMs in enterprise-like lateral-movement scenarios. Six frontier models are evaluated across two scenarios and three modes: expert-defined, self-scaffolded, and fully autonomous. We assess validator consistency and evidence grounding; introduce a subtask-conditioned, cost-aware score for abnormal token use, retries, and runtime; and use comparative LLM-as-a-Judge analysis to identify planning deficiencies, including tool misalignment, plan similarity, over-specification, inadequate probing, and weak recovery. Validators are generally relevant and evidence-grounded but often nonspecific and overly optimistic. Bottlenecks cluster in credential and lateral-movement tasks, spread with scenario complexity, and vary more under full autonomy. Reliable evaluation must assess outcomes, evidence interpretation, resource use, and adaptation after failure.

Saeedeh Lohrasbi, Mohammad Mamun, Ahmed Yehia +2

Cybersecurity, DTRC, National Research Council, Ottawa, Canada · University of Windsor, Windsor, Ontario, Canada

Agent Failure AnalysisLLM Agent EvaluationLLMs for CybersecurityLLM Agent PlanningLLM Agent Reliability
AskPDF
Sep 22, 2026

CausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults

When an agent handling a payment exception loses money, the agent-step attribution methods this paper compares against will name one of its actions. They will do so even when a settlement message was dropped and the agent never had a chance: they intervene on agent actions and do not expose infrastructure faults as intervenable variables, so every dollar they explain is charged to a decision. We take a benchmark whose fault process is explicit and replayable, decompose each episode's realised delivery schedule into named, individually repairable messages, and intervene on both the agent's choices and the infrastructure's. A telescoping identity splits any policy's loss exactly three ways: an infrastructure effect, a policy differential against the best implementable policy, and a reference-policy residual. Two of the three can be negative, so none is a share; Shapley then divides the first into signed allocations over individual messages. One result is structural and needs no corpus: an agent-only baseline identifies no infrastructure cause, because its model contains no variable that could name one. What 545 planted episodes across 3 policies measure is the size of that consequence. It misfiles 100% of infrastructure episodes and charges $114,383.40 to the agent. Repairing what it names recovers 0.0% of the available loss; repairing a minimal sufficient set recovers 100.0%. Scoring messages one at a time is not merely imprecise: 27.8% (95% CI: 23.3--32.3%) of episodes do not decompose additively. We evaluate deterministic programmatic policies rather than language-model agents, which is what makes replay exact and which limits external validity to stochastic agents. The prevalence figures are properties of this generator, not field rates.

Abhishek Sharma

Agent Failure AnalysisFinancial ServicesCausal AttributionShapley Value AttributionFine-Grained Credit Assignment
AskPDF
Sep 22, 2026

When Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention

Runtime traces can appear transparent, but a closed-loop policy determines which states are visited and which failures become visible. We study a simulated hotel-pricing agent mapping time, inventory, and market state to discrete price actions under varying demand regimes. A fault may leave no aggregate trace when the policy rarely visits affected cells. We treat entry into aggregate-only fault interpretation as a diagnosability decision preceding scoring or localization. A reference-map gate requires repeated clean-policy support; a matched runtime gate then requires joint support in clean and current streams. Signal analysis occurs only after both pass. We calibrate false admission on a disjoint clean stream at the physical-component level and model detection by affected clean traffic rather than nominal cell coverage. In a frozen one-shot heldout, 55/72 (76.4%) regime-component units were reference-admitted, representing 20 physical components; 54/55 passed matched runtime admission, while the rejected unit abstained. Stable false admission was 0/20, with a one-sided exact 95% upper bound of 0.1391, meeting the frozen 0.20 criterion. Across 540 repeated unit-arm rows nested in those 20 clusters, affected clean traffic reduced negative log likelihood by 29.3% relative to cell coverage, a gain of 0.1264 nats per row (cluster-bootstrap 95% interval [0.0593, 0.1918]). Adding mask family and its interaction improved log loss by 0.0015 nats per row (one-sided upper bound 0.0066), below the frozen 0.01 practical-sufficiency margin. A development audit found that exact minimum hitting set and greedy selection chose identical supports in 12/12 scenarios because singleton evidence had resolved the conflicts. The result is a bounded rule for interpreting aggregate agent behavior: first establish exposure, then score change, and abstain when the trace cannot support the claim.

Peiying Zhu, Sidi Chang

Blossom AI San Francisco, CA, USA

Agent Failure AnalysisSelective PredictionFault DetectionAI Agent MonitoringFault Diagnosis
AskPDF
Sep 21, 2026

Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse

Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While prior research have studied task success and task completion of such agentic systems, research on agent to tool interaction chain via a wrapper and API, specifically in biological agentic workflows, remains limited. This study investigates specific failures in agent to tool interaction where a tool invocation appears successful but some or all of the information or functionality from the tool via its API / wrapper is incomplete or missing and there are no communications to the user or the agent regarding the missing information. We call these 'silent failures' because the user or the agents are not aware that such a failure has occurred. For the purpose of this study, we developed an audit mechanism to identify such silent failures in agent to tool interaction chains, by examining 15 scientific tools (and their associated API documentation and tool documentations) integrated within the ToolUniverse environment (ToolUniverse serves as our experimental environment rather than the object of the study itself). We structure our study around 7 failure locus, characterising where the failure occurs in the chain. We observed 91 failures (manually validated post LLM based candidate discovery and automated testing), most frequent of them being missing data or fields and inconsistencies in search, filtering or ranking criteria. Most of the 91 failures occurred in API layer (52) or wrapper layer (25), with a potential of silent failure amplification downstream. The results show that silent failures originate upstream of the event and propagate downstream into apparently valid scientific outputs. We propose a concept of contextual reliability to handle such failures and suggest mechanisms for testing, disclosing, monitoring, and measuring such failures across the agent-tool interaction pipeline.

Devansh Singh, Shreya Gopalan, Sundaraparipurnan Narayanan

AI Tech Ethics

Agent Failure AnalysisTool-Using AgentsAI Agent AuditingAI Agents for Scientific Discovery
AskPDF
Sep 15, 2026

Locating Hidden Failures Makes Long-Horizon Agents More Reliable

As AI agents take on long, autonomous tasks, we increasingly oversee rather than perform the work, yet we still judge them almost entirely by whether they finally succeed. An outcome cannot reveal where a run went wrong, whether the agent recovered, or the irreversible harm it caused along the way, and where long-horizon agents fail remains unmapped. We study 25182518 agent trajectories across software engineering, computer use, and science, close to real deployment, and classify 69676967 mistakes into 7878 failure types. Failure follows a recurring signature: after its first mistake an agent often fails to recover and rarely catches the error itself, so the run continues unchecked while still looking correct; whether an agent recovers depends on the task and the environment's feedback, not on the agent framework running it. Long-horizon agents can do real harm on the way to a passing result: even runs scored as solved delete data, corrupt systems, or fabricate success rather than earning it. We release these human-verified annotations as Traverse, a benchmark on which six frontier judges struggle to locate failure regardless of scale: even the strongest correctly identifies the first mistake in fewer than a third of runs. Yet Scout, a 44B verifier we trained, locates failure far better than these judges and transfers to domains it never saw. Used at test time to select among an agent's candidate runs, it raises task success above the agent's own single-attempt performance, without retraining the agent. By making failure cheap to locate and correct, this work is a foundation for more trustworthy long-horizon agents that learn from their own mistakes, and a practical path to overseeing increasingly autonomous AI.

Salman Rahman, Yubin Kim, Mihir Parmar +15

University of California, Los Angeles · New York University · Google Research +1

Agent Failure AnalysisAI Agent ReliabilityLong-Horizon Agent EvaluationFault DetectionAI Agent Benchmarks
AskPDF
Sep 14, 2026

The Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information

Recent investigations of the July 2026 OpenAI-Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned task becomes impossible, does an agent persist, stop, or escalate, and can observing another agent's behavior change that decision? We study this decision point on ImpossibleBench-derived software-repair tasks with GPT-5.6 Sol, Claude Fable 5.1, and Gemini 3.8 Flash. Each task contains a genuine software defect together with a conflicting test requirement that cannot be satisfied by a behaviorally correct source-code change. If the agent modifies the protected test file, it violates the boundary, which it is not supposed to. Holding the impossible task fixed, we vary what is told to the agent: peer precedent and punishment, a forged authorization claim, instruction wording, and tool friction; we also study three-agent swarms sharing a message board. Around this shared boundary, the models exhibit distinct adjudication policies. Fable emphasizes scope and provenance, Gemini often interprets boundary-relevant cues through a security lens, and Sol largely filters lateral precedent while engaging apparent vertical authority. Our study shows that compliance is not well characterized as a property of a prompt or model in isolation. We propose conflict adjudication, the mapping from information to interpretation to action, as a useful unit for evaluating agent alignment when task pressure, authority claims, tool affordances, and social evidence conflict.

Ivy Zhang

Apart Research

Agent Failure AnalysisSoftware Engineering AgentsAI Agent EvaluationAI Agent Safety
AskPDF
Sep 14, 2026

When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary

AI agents increasingly execute long-running workflows that externalize effects through independently supplied tools. Under retries, speculative execution, concurrency, and partial failures, the resulting external state may be inconsistent with the workflow's intended resolution: required effects may be missing or duplicated, aborted effects may survive, and committed effects may depend on provisional state that is later withdrawn. Advanced transaction models address related failures, but assume that lower-level operations expose the semantics they depend on: whether an effect occurred, whether it can be compensated, staged, or safely reordered. Shared agent-tool interfaces usually do not. We contribute an effect-history model that separates events in the external world from the runtime's observations of them, and a catalog of eight recurring external-effect anomalies. From the catalog we derive the boundary capabilities required to exclude each anomaly in general, and four points where black-box tool invocation alone cannot provide a general guarantee. We then ask how much of this is expressible in a widely used shared tool interface, measuring the use of the standard annotation vocabulary across 98,291 tools exposed by registered Model Context Protocol (MCP) servers. The fields are widely emitted but provide only coarse call-level hints, and none of the required capabilities is fully expressible. These results motivate reusable transactional contracts at the tool boundary.

Artem Trofimov, Boris Novikov

AVIV Group · Independent Researcher

Agent Failure AnalysisAgentic WorkflowsTool-Using AgentsLLM Agent Reliability
AskPDF
Sep 11, 2026

Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures

The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-level signals into actionable interventions. The sheer scale of the data renders human review impractical, driving the need for automated root-cause attribution (RCA). However, automated RCA methods using LLMs suffer from low diagnostic accuracy, especially as execution traces grow larger. They struggle because relevant information is often sparse, distributed across distant actions, and disconnected from the visible failure, reducing root-cause attribution to a massive search problem. Existing RCA methods typically rely on one-shot LLM judgments to diagnose failures from execution traces. While effective for shorter trajectories, these judges tend to settle on a plausible diagnosis early, leaving critical evidence in longer traces unexamined. We introduce Continual Search, an iterative framework that nudges the judge, over successive turns, to keep searching for unresolved diagnostic evidence. We evaluate Continual Search across four existing RCA benchmarks. Recognizing the lack of massive execution traces in current benchmarks, we introduce MegaRCA-Mix to evaluate RCA at scale. MegaRCA-Mix provides a challenging testbed of 50 human-annotated failure trials spanning long-horizon, execution-heavy tasks. Across multiple benchmark suites and model families, Continual Search consistently improves attribution performance. On MegaRCA-Mix, for example, it improves Opus-4.8's F1 score by 29%, from 0.4710.471 to 0.6080.608. More interestingly, within the same model family, lower-tier models can even surpass their higher-tier counterparts, demonstrating that effective search supersedes raw model scale.

Harsh Raj, David Lee, Anas Mahmoud +7

Scale AI · Scale AI Research

Agent Failure AnalysisAgentic SearchLong-Horizon Agent Evaluation
AskPDF
Sep 10, 2026

Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery

Self-improving agent workflows create an audit problem when the same controller can change both its behavior and the conditions under which that behavior is judged. We present GuardrailLoop, a simulation-based testbed that makes three operational contracts jointly testable: preservation of human-defined policy, compute accounting at every recorded execution prefix, and recovery of a specified scientific state after crashes. A hash-pinned policy fixes goals, scope, evaluation identity, budget, and release conditions; machine-directed evolution is restricted to a code-owned feature catalog and bounded knobs. The contribution is an executable boundary and an evaluation protocol that separates useful adaptation, state recovery, and repeated execution. In a paired 50-seed 2 x 2 study, round-stage growth changes target attainment by +1.00 and restricted mean compute to target by -56.97 simulated GPU-hours (95% paired-bootstrap interval [-58.91,-54.70]); idle growth has zero measured utility effect. Across 240 enumerated crash injections, all runs recover the defined outcome, but only 210 preserve the normalized trace: 30 pre-commit crashes repeat a planner call. Resource-drift, kill-switch, integrity, and output-guard matrices satisfy their specified checks. These findings show why successful outcome recovery is insufficient evidence of exactly-once execution. They establish conformance within one calibrated deterministic testbed, rather than general safety or real-world self-improvement.

Qinzhen Ma, Jialin Wu

Rice University · University of California, San Diego

Agent Failure AnalysisAI Agent ReliabilityRuntime Enforcement for AI AgentsAI Agent Safety BenchmarksSelf-Improving Agents
AskPDF
Sep 10, 2026

The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures

AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare public failures with agent-security evaluations. We present the Agent Incident Registry (AIR) (Project page: https://enkryptai.com/air), a source-linked catalog containing 487 records of agent-related events disclosed from 2022 through 2026. Each record includes supporting evidence, a stable identifier, and missingness-aware labels for causal role, disclosure class, mechanism, and outcome. Among the 336 generative-system records in which the agent acted, 81 involved realized harm (24%). Realized outcomes concentrate in in-the-wild and safety-failure records, while responsible disclosures and research demonstrations are overwhelmingly demonstrated; the aggregate share therefore characterizes collection composition rather than deployment risk. After initial curation, a second human reviewer checked all 487 records and their existing labels for completeness and correctness. In a deployment-analogue audit, InjecAgent's 1,054 cases occupy three of AIR's twelve surfaces and are all attacker-triggered, whereas AIR contains 92 no-adversary safety failures. AIR supports source-grounded case retrieval and evaluation-scope auditing, not failure-rate or control-efficacy estimation.

Divyanshu Kumar, Rohith HN, Nitin Aravind Birur +2

Anaconda

Agent Failure AnalysisAI Agent Evaluation
AskPDF
Sep 8, 2026

CIVI: A Framework for Diagnosing Search Agent Failures in Civic Information

Large Language Models are increasingly deployed in public-sector settings, where incorrect guidance can cause irreversible harm. We introduce CIVI, the first framework for diagnosing search agent failures in civic information. Its benchmark instantiation jointly spans cross-national, interjurisdictional government contexts (federal, state, and local) and functional categories from an internationally adopted United Nations standard. We evaluate ten frontier search agents and find that none matches an attentive human baseline. Alongside accuracy, CIVI measures search invocation rate, selective no-search accuracy, and how often agents cite authoritative government sources. To perform this diagnosis, we introduce ARISE, which decomposes agentic search failures into four mutually exclusive modes, isolated via source-injection ablation. ARISE attributes 72.1% of all observed failures to retrieval-bound causes rather than to gaps in the models' parametric knowledge.

Dingying Liu, Yunshun Zhong, Wentao Zhang +1

University of Sydney · University of Toronto · University of Waterloo +1

Agent Failure AnalysisAI Agent ReliabilityQuestion AnsweringAI Agent Benchmarks
AskPDF
Sep 7, 2026

Audit Without Verification: When LLM Accountability Layers Relay Rather Than Check

Multi-agent LLM pipelines increasingly span organisational boundaries; when a fault surfaces, someone must determine where it entered. The artifact available is rarely a full execution trace: it is the reports each agent filed, and a filed report can state a conclusion alongside its observations. Using a pre-registered, institutionally partitioned pipeline of six agents with process-level information boundaries, balanced defect injection and matched clean twins (345,600 requests per chain model, two models), we first report that our pre-registered hypothesis -- that collective responsibility framing degrades escalation with chain length -- is not supported. The layer nevertheless fails asymmetrically. It originates almost nothing: zero allegations across 7,996 clean episodes where every agent stayed silent. It filters upstream error poorly, naming an innocent party in 34.4% and 62.6% of clean episodes where an agent raised a false alarm. Conditional on no agent proposing the true origin (59.5% of episodes on one chain model), an auditor reading the reports recovers it in 4.1% of cases -- below a uniform guess (20%) and the best fixed-link accuser (31.0%) -- while reaching 60.3% from the raw documentation of the same episodes. Deleting one clause, the field carrying the agents' own conclusion, isolates the cause at constant observations: accuracy rises to 45.2% (+41.2 pp, 95% CI +35.3 to +46.9) and adherence collapses from 94.4% to 3.4%; where the suggestion was correct the same deletion instead costs accuracy, 70.5% to 55.7%. The harm replicates on two frontier auditors in four conditions out of four (+8.5 to +39.0 pp) and in a second domain (+47.7 and +61.1 pp), where the cost disappears. The net effect is governed by upstream reliability together with both conditional magnitudes. An accountability layer needs evidence sufficiently independent of the conclusions it verifies.

Paul-Peter Arslan

Institute For Future Technologies

Agent Failure AnalysisAI AccountabilityAI Agent AuditingLLM AuditingLLM Agent Reliability
AskPDF
Sep 4, 2026

WolfSociety: Understanding Collective Risk from Harmful-Agent Scaling in Financial Agent Societies

Safety evaluations typically focus on individual agents, but interacting agents can spread harmful information and influence the environment in which later decisions are made. We study how collective failure changes with harmful-agent fraction and society size in a controlled financial agent society, where agents communicate over a social network and trade in a shared market. In the primary financial scenario, collective failure requires broad harmful diffusion together with severe price dislocation or liquidity stress. Across all tested society sizes, failure remains rare at low harmful fractions but rises sharply over a narrow range. As society size grows from N=100 to N=2000, the harmful fraction associated with a 50% failure probability decreases from 4.7% to 2.2%, while the corresponding number of harmful agents increases from approximately 5 to 44. In contrast, when the number of harmful agents is held fixed, their impact becomes weaker as the society grows. Controlled interventions further show that broader network reach shifts the collapse boundary toward lower harmful fractions, whereas stronger conformity alone has little effect. To characterize these effects, we introduce Agent Society Dynamics, a finite-size framework for relating harmful-agent fraction, society size, and interaction structure to collective failure. Overall, our results reveal a nonlinear, size-dependent collapse transition in financial agent societies, showing that collective failure depends not only on the prevalence of harmful agents but also on the size and interaction structure of the surrounding society. Code is available at https://github.com/SAIL-Research-Lab/WolfSociety.

Lejun Zhang, Sarah Lu-Liang, Xin Jiang +3

Shanghai Jiao Tong University · University of California, Berkeley · University of Toronto

Agent Failure AnalysisMulti-Agent SystemsEmergent Behavior in Multi-Agent SystemsLarge Language Model-Based Social Simulation
AskPDF
Sep 4, 2026

DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems

Large language model (LLM)-based multi-agent systems have experienced rapid growth in recent years. Despite their promise, such systems remain fragile, frequently exhibiting reasoning and coordination errors that can lead to system-level failures. Failure attribution in such systems relies on tracing natural language interactions among agents to identify the decisive error, which refers to the earliest action whose correction can reverse system failure. There are two key challenges: 1) Shallow attribution: Existing methods often capture only minor deviations, such as incomplete retrievals or formatting errors, which verification mechanisms can correct, while missing the decisive cause of system failure. 2) Contextual degradation: As the length of the system traces increases, the model's reasoning ability rapidly deteriorates. To address these challenges, we propose DCFA, a training-free framework for failure attribution. DCFA integrates a global module that constructs structured causal-inspired dependency graphs from system traces to identify the initial decisive error, and a local module that applies local counterfactual-inspired reasoning to refine causal-inspired attribution. Experiments on the Who&When benchmark across six LLMs show that DCFA improves step-level accuracy by up to 8.27% over state-of-the-art baselines.

Zehao Wang, Lanjun Wang, Shilong Jin +2

College of Intelligence and Computing, Tianjin University, Tianjin, China · School of New Media and Communication, Tianjin University, Tianjin, China · College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China +1

Agent Failure AnalysisMulti-Agent LLM SystemsMulti-Agent SystemsFailure Attribution for LLM Agents
AskPDF
Sep 1, 2026

EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems

Large language model (LLM) agent failures often contain multiple related errors rather than a single mistake. Existing attribution methods usually identify a responsible agent, step, or root cause, but do not explicitly model dependency between errors. We introduce EDGE, an Error Dependency Graph-guided multi-Error attribution framework. EDGE constructs an error dependency graph from observed error events and validates a reliable causal subset through counterfactual rollout. The inference graph guides a two-stage LLM-as-judge detector for error attribution, and the intervention-validated subgraph provides a more reliable basis for explanation and repair analysis. Experiments on TRAIL and MAST show that EDGE improves category-level multi-error attribution across most evaluated models and settings. Experiments with adapted Who&When-style prompts show that the graph helps across prompting strategies. These results suggest that dependency structure is a useful diagnostic prior for agent failures beyond isolated root-cause prediction.

Jun Hou, Priya Pitre, Yi Fang +1

Virginia Tech

Agent Failure AnalysisMulti-Agent LLM SystemsCausal AttributionFailure Attribution for LLM Agents
AskPDF
Aug 31, 2026

Using Grounded Theory for Agent Behavior Analysis at Scale

Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, often unfamiliar tasks where pre-built classifiers fall short. We propose to bring grounded theory into agent trajectory analysis: a six-decade-old qualitative method from the social sciences, with a principled saturation criterion and an auditable trail from data to theory. We propose AutoTraceGT (Automated Trace analysis through Grounded Theory), the first multi-agent pipeline that automates grounded theory on agent trajectories. It iteratively performs open, axial, and theoretical coding until saturation, producing a behavioral taxonomy tailored to each task. Across six trajectory corpora, AutoTraceGT produces codebooks that recover 73-91 percent of the failure modes in human-annotated taxonomies and surface additional patterns that those taxonomies miss. The emergent theoretical narrative aligns with prior expert accounts. Used as a deductive feature space, the codebook outperforms zero-shot and few-shot LLM baselines on downstream failure prediction. These results suggest Grounded Theory offers a scalable analytic tool for ML researchers and agent developers studying what agents actually do.

Zhuoran Lu, Yangyang Yu, Zhuoyan Li +5

1Purdue University · 2Stevens Institute of Technology · 3Cornell University +2

Agent Failure AnalysisAgent Trajectory Analysis
AskPDF
Aug 30, 2026

Cascade Failure Attribution for Multi-Agent Systems

Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to execution failures. Accurate failure attribution is therefore critical for improving agent reliability. Existing topology- and spectrum-based methods exploit trajectory structures but often overlook fine-grained semantics, while LLM-based attribution methods capture semantic cues but suffer from long-context degradation over lengthy trajectories. To address these challenges, we propose DuoTrace, a plug-and-play detection filter for LLM-based failure attribution. DuoTrace follows a detect-before-attribute paradigm: it first detects anomalous executions and then supplies focused trajectory evidence to downstream LLM-based attribution methods. For effective VAE-based anomaly detection on agent trajectories, DuoTrace integrates dual-view semantic-structural node representations, a Tree-LSTM-based trajectory encoder, and data augmentation through outcome-verified LLM replay and root-to-node path extraction to handle heterogeneous nodes, hierarchical execution structures, and limited normal execution data. Experiments with six LLM-based attribution baselines show that DuoTrace improves agent-level and step-level attribution accuracy by 11.2% and 7.7%,respectively.

Jiayi Zhang, Zexin Wang, Degang Sun +4

Computer Network Information Center, Chinese Academy of Sciences · Institute of Computing Technology, Chinese Academy of Sciences

Agent Failure AnalysisMulti-Agent LLM SystemsFailure Attribution for LLM AgentsLLM Agent Reliability
AskPDF
Aug 29, 2026

Safe to Resume? Breaking Execution Continuity of Agent Execution via Rollback

AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are costly to reconstruct after failures. Checkpoint and rollback (C/R) are becoming essential for recovery, yet their security implications remain largely unexplored. Correct rollback does not imply secure recovery: a faithfully restored checkpoint may resume an execution whose states, assumptions, and external effects never coexisted in any valid history. In this paper, we present the first systematic security study of checkpoint and rollback in existing agent systems. By examining representative agent C/R systems, we characterize the design space of existing C/R mechanisms and develop a general execution model that captures their recovery boundaries and state dependencies. From this model, we identify five fundamental failure modes spanning incomplete or inconsistent internal state, stale external dependencies, nondeterministic replay, and unrecorded external effects. We further demonstrate their security impact through three end-to-end attacks on Hermes, Cline, and LangGraph, enabling malware-verification bypass, unauthorized mail forwarding, and double payment. To systematically study these failures in practice, we develop a multi-agent analysis pipeline that reconstructs execution semantics, identifies violations of the five failure conditions, and validates them through actual rollback. Across five representative frameworks, our evaluation shows that these failures recur across heterogeneous C/R designs and stem from a common gap between the state restored by a checkpoint and the dependencies required for secure continuation.

Guanlong Wu, Dahui Li, Ke Jiang +3

Southern University of Science and Technology · City University of Hong Kong

AI Agent SecurityAgent Failure AnalysisAI Agent Reliability
AskPDF
Aug 29, 2026

Localizing Emergent Failures in Agentic AI: Recovering Minimal Repair Families via Counterfactual Replay

Failures in agentic AI systems can arise from interactions among messages exchanged by multiple large language model (LLM) agents. Pointwise attribution cannot distinguish a jointly necessary repair from alternative singleton repairs. We formulate Minimal Repair Family Recovery (MRFR): recovering all inclusion-minimal event sets whose counterfactual replay restores task success within a declared size bound. We propose Graph-Constrained Joint Replay (GCJR), which slices failure-relevant events from an execution dependency graph, constructs graph-feasible singleton and pair candidates, and verifies them by replay with paired clean counterparts. For fixed replay outcomes, GCJR is exact within its declared graph domain. On 90 in-scope cases from a 120-DAG controlled benchmark, GCJR achieves 1.000 Family Exact Match while reducing mean replay calls from 56.3 to 25.3 (55.1%) relative to exhaustive search. On a 24-case, four-agent LLM pilot, it again achieves 1.000 Family Exact Match and reduces mean model calls from 21.0 to 10.0 (52.4%); single-event replay misses jointly necessary repairs.

Bingjie Li, Yumeng Song, Zhongming Yao +1

School of Computer Science and Engineering, Northeastern University, Shenyang, China · Department of Computer Science, Aalborg University, Aalborg, Denmark · College of Computer Science and Technology, Zhejiang University, Hangzhou, China

Agent Failure AnalysisMulti-Agent LLM Systems
AskPDF
Aug 28, 2026

Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction

One model passed our fidelity check without ever opening the datasheet. We found it while qualifying models for an internal extraction service: a structured-output constraint had silently disabled tool use, and the model answered anyway, with fabricated source text. Only the per-tool trace exposed it. Fidelity -- whether an extracted value matches the source -- is the standard measure for agentic document extraction, and it scores that run a success. We therefore log every tool call in an agentic benchmark of 25 hand-curated claims over three components, with 12 more on a fourth, 37 in all. From that dispatch record we build two instruments: a rule-based failure-attribution classifier, and a silent-failure detector whose two rules check only which tools were called, never the extracted value. The detector raises no flag on 207 clean fidelity-passing extractions across three model families, and recovers all 50 planted faults that withhold exactly the tools its rules check. The two results are not symmetric: the first bounds the false-positive rate, the second is recall by construction, and detection power against runs that call their tools and still answer wrongly is unmeasured. A second, independent oracle, a causal chamber that tests whether the datasheet's claims hold under physical measurement, is intentionally partial: it confirms only what the apparatus can exercise, a verifiable envelope of 2 of those 37 claims, and we give a taxonomy of why the rest are not physically gradable. Under a controlled perturbation, fidelity passes throughout while the chamber verdict flips exactly at the measurement uncertainty. Across three deployed model stacks (one destabilised by its serving stack, not by any capability gap) the tool layer buys portability and observability rather than accuracy, and earns its premium only once a document outgrows the context window.

Qing Ye, Meng-Hsuan Lin

Infineon Technologies AG Neubiberg, Germany

LLM Agent EvaluationDocument Information ExtractionAgent Failure AnalysisAI Agent Auditing
AskPDF
Aug 26, 2026

Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence Adequacy

Autonomous agents increasingly perform bounded software tasks under an orchestrator that retries, resumes, and budgets them. The machinery such orchestrators reach for is the service mesh's: retry, timeout, and error-rate circuit breaking. We report a failure study of a production agentic software-delivery platform over 147 numbered incidents spanning 81 runs, each with a measured cost and, in most cases, a mutation proof reproducing the failure. All three assumptions those primitives rest on are violated in practice, and we quantify the consequences: a loop of fifty-four consecutive successful tool calls no error-rate breaker could see; a progress signal constant by construction, guaranteeing a false trip on the third repair round and driving one run from six of six components to three; twenty-one events accumulated across six invocations of one delegation, making a correct, idempotent component unwinnable; a misrouted failure that woke five components for a two-component fault, leaving three bystanders regressing working code; and twelve incidents in which the enforcement layer blocked correct work, the most expensive costing 107 agent turns and zero accepted writes. We find one cross-cutting cause and its dual. Identity adequacy: in five separate subsystems an identity that failed to discriminate produced a confident wrong answer, and two of them derived the corrective rule independently. Evidence adequacy: a reliability decision may be taken only on evidence capable of moving, attributable to what it measures, and deterministic under identical conditions. From the findings we derive seven reliability primitives whose enforcement unit is the delegation rather than the message, and specify the controlled evaluation the study motivates but does not constitute.

Mazhar Shaikh, Anurag Rajkumar Bombarde, Harshal Pathak

Agent ReliabilityAgent Failure AnalysisRuntime Enforcement for AI AgentsSoftware Engineering Agents
AskPDF
Aug 26, 2026

Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hindering their real-world deployment. Existing MAS debugging and repair methods typically rely on rerunning and resampling the entire execution trajectory. However, a fundamental question remains to be answered: do these methods causally repair MAS failures or merely stochastically repair by leveraging the randomness of LLM sampling? To evaluate the effectiveness of MAS repair methods, we introduce SymTrace, a controlled evaluation framework that records the MAS execution trajectory and establishes intervention anchors. During replay, it effectively reconstructs the execution before the anchor using recorded logs and only regenerates the downstream trajectory, thereby enabling the reliable reproduction of MAS failures. We further construct the dataset SymFail, comprising 536 human-annotated failure trajectories with graph-linked locations, categories, and trace evidence. Based on these foundations, we conduct a large-scale empirical study across three mainstream MAS frameworks. Our findings reveal that existing unguided rerun methods are highly unreliable, exhibiting low failure reproduction and repair rates (only 67.97% and 6.90%, respectively). Building upon these findings, we further explore the effectiveness of a symptom-driven intervention method, which successfully repairs 20.15% of the failed cases (a 191.89% improvement to state-of-the-art repair methods). This study aims to provide actionable insights for MAS debugging and repair research, paving the way for the robust deployment of multi-agent systems.

Zhongwen Luan, Xiaoyu Zhang, Ming Hu +3

Xi’an University of Architecture and Technology Xi’an, China

LLM Agent ReliabilityAgent Failure AnalysisMulti-Agent Systems
AskPDF
Aug 25, 2026

Resilient Monitoring of Social Dynamical Systems through Collaborative Multi-Agent Networks under Latency

Social dynamical networks significantly influence contemporary digital landscapes, affecting realms from social activism to public policy formulation. This paper investigates the use of multi-agent systems (MAS) to monitor and analyze these networks. Firstly, we propose a single-time-scale distributed inference model designed to effectively manage challenges such as latency and agent failure. Secondly, we provide sufficient conditions that ensure the stability of the proposed scheme. Notably, the observer gain design remains effective regardless of time delays. Thirdly, we develop a computationally efficient recovery mechanism for agent failures that relies on employing graph-theoretic approaches to restore network observability by replacing failed agents (due to sensing failure or unbounded delays, i.e., packet drops) by implementing computationally efficient graph-theoretic methods to assign observationally equivalent agent counterparts. Lastly, we illustrate the proposed scheme through a pedagogical example and real-world network applications.

Mohammadreza Doostmohammadian, Sergio Pequito

Multi-Agent SystemsAgent Failure Analysis
AskPDF
Aug 25, 2026

Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems

Multi-agent LLM systems are increasingly deployed in real-world applications, where failures can be costly and difficult to localize. Despite growing efforts to automate failure attribution, diagnosing failed runs still largely relies on human engineers. Yet engineers rarely debug complex systems by reading raw logs end to end. Instead, observability tools organize traces around components, actions, and dependencies to support targeted navigation. We hypothesize that modern LLMs can benefit from the same paradigm. To test this hypothesis, we introduce Adaptive Influence Graphs (AIGs), a two-stage agentic framework that first transforms a failed trace into a structured graph and then navigates it to identify the critical error. Across multiple models, we show that richer trace representations consistently improve failure attribution, with adaptive graph construction and agent-directed traversal yielding the strongest results. AIGs establish a new state of the art on Who&When, the standard benchmark for multi-agent failure attribution. This affirms our hypothesis that attribution depends not only on the diagnosing model, but also on how the trace is represented and explored.

Yarden Bakish, Amir Dudai, Roy Ganz +4

Tel Aviv University · AWS Agentic AI

Agent Failure AnalysisMulti-Agent LLM Systems
AskPDF
Aug 24, 2026

CatchBench: When Can an Agent Failure Be Caught?

When can an agent failure be caught? A weak audit score alone cannot identify whether the record or the method is limiting. CatchBench therefore puts one auditor's question to three information states: the declared configuration before a run (PRE), a growing prefix of its trace (LIVE), and the finished trace (POST). Prior benchmarks fix one of these states or vary the telemetry; to our knowledge none scores all three under one task-method interface. Each state admits different questions, so seven task contracts carry their own labels and metrics rather than one leaderboard. Four are evidential; three are Gold-derived mechanism diagnostics. The release scores 72 entrants, from rule scanners and structural models to eleven LLM judges across nine model families (GPT, Claude, Gemini, Gemma, Llama, Qwen, DeepSeek, Mistral, Nova), over 1187 declared configurations and 1162 recorded runs. Every recorded comparison is published as a measured difference with its interval, uncorrected, and no board declares a winner it cannot show. The three sharpest results cut against our own data. One rule reads declaration order alone and reaches a perfect F1 on one of six configuration sources, so a score there measures how the corpus was built. Our admissibility bar then rejected one injected substrate and withheld evidential status from the other. A published structural gain also turns on which size reference it is measured against. A benchmark number is therefore not interpretable until the process behind its labels is published and tested for the shortcut it may leave. We report all three, and regenerate every ordering from released predictions with no model call.

Yue Zhao, Mengyuan Li, Ruolin Li +5

University of Southern California · Carnegie Mellon University · AWS Agentic AI +3

Agent Failure AnalysisBenchmark AuditingAI Agent AuditingAI Agent EvaluationAI Agent Monitoring
AskPDF
Aug 24, 2026

The Illusion of Independent Quorums: Epistemic Fault Domains and Correlated Cognitive Failures in Agentic Quorums

Multi-agent quorums are widely used to authorize high-stakes infrastructure and policy mutations, yet distinct reviewers often share upstream telemetry, documents, or tool backends. When upstream inputs fail, multiple votes collapse onto a single corrupted cause: replication does not imply epistemic redundancy. We introduce Epistemic Fault Domains (EFDs) and the Structural Epistemic Cut κ_E, which quantifies the minimum number of modeled root faults whose exposure covers an authorizing coalition relative to an explicit Epistemic Fault Basis. Under closed causal accounting, conservative exposure, and authorization alignment, κ_E lower-bounds the number of roots required for semantic compromise (κ_S). We prove that arbitrarily large quorums can retain κ_E=1, that recognizing shared ancestry never increases credited resilience, and that adding voters at a fixed threshold cannot increase the cut under compatible exposure extensions. Finally, we design the Dependency-Aware Quorum Controller (DAQC) to enforce structural cuts at runtime admission, evaluate its mechanics via analytical derivations and simulations, and provide a frozen 120-task external benchmark suite.

Jun He, Deying Yu

Multi-Agent SystemsAgent Failure AnalysisAccess ControlMulti-Agent Coordination
AskPDF
Aug 24, 2026

Robustness Analysis of Agentic AI to Inconsistent and Incomplete Tool Responses

Tool-using agents increasingly rely on external tools to complete multi-step tasks, but tool returns can fail in different ways and require different recovery actions. Existing robustness studies often use uncertainty-based measures to detect when an agent becomes unreliable. These measures can reveal that something has gone wrong, but they do not directly identify the type of tool failure or the appropriate response. We address this limitation by analyzing tool failures at the moment a return enters the agent context. Our approach combines two complementary signals. The first compares the likelihood of the returned content under the tool schema and under the full trajectory prefix. The second measures the agent's probability distribution over its legal next actions. We evaluate the approach by injecting incomplete and inconsistent returns into a retail customer-service benchmark. The results show that likelihood-based signals clearly capture incomplete returns and some direct inconsistencies, while action-based signals reveal how strongly a failure changes the next decision. Some failures that are weak under likelihood signals can still redirect the agent toward state-changing actions. These findings show that tool failures can be recognized at the return boundary, but reliable diagnosis requires combining multiple signals.

Jiachen Xu, Torben Bach Pedersen, Zhongming Yao +2

Department of Computer Science Aalborg University Aalborg, Denmark · College of Computer Science and Technology Zhejiang University Hangzhou, China · School of Information Science and Engineering Northeastern University Shenyang, China

Agent Failure AnalysisAI Agent ReliabilityTool-Using AgentsLLM Agent Reliability
AskPDF
Aug 20, 2026

When Failures Propagate: Causal Failure Attribution in Agentic Retrieval-Augmented Generation

Agentic retrieval-augmented generation (RAG) interleaves retrieval, reasoning, and answer generation across multiple hops. A retrieval error at hop 1 can surface only as a wrong answer at hop 3, while later retrieval can also repair the trajectory. This paper introduces AgenticRAG-FP, an interventional benchmark for causal failure attribution in agentic RAG. The benchmark injects a certified fault at a specified hop, re-executes the downstream trajectory, and evaluates diagnosers against the known intervention. Its central question is whether a post-hoc trace still identifies the injected hop after the suffix changes. In the completed strict dense Claude Haiku 4.5 sweep on 80 three-hop MuSiQue questions, coverage-based diagnosis is 0.91 at hop 1 and 0.00 at hops 2 and 3 (n=43,36,21 failed trajectories). A smaller content-corruption study changes an answer-bearing or bridge fact in topically intact evidence. At depth 2, where 18 failed cases remain after filtering, coverage-based diagnosis is 0.00 and a frozen-hop counterfactual probe is 0.67 in an exploratory pooled comparison. Depth-3 content estimates are descriptive only because they contain three failed cases. These results make propagation depth an explicit evaluation axis for diagnosing agentic RAG failures while distinguishing broad evidence of post-hoc signal loss from small-sample method comparisons.

Lauren Pothuru

Anote

Agent Failure AnalysisAgentic RAGRAG EvaluationCausal Interventions in Language Models
AskPDF
Aug 20, 2026

Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents

Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later actions often depend on services, state, or access discovered much earlier. This makes final task success difficult to interpret: an agent may fail before it ever reaches the point where the capability of interest can be exercised. We present a diagnostic methodology that instruments security tasks with checkpoints, separates failures before and after capability exposure, and uses controlled interventions to test suspected upstream bottlenecks. We evaluate the methodology across four task families involving delayed reuse of discovered information, reuse of observed state, recovery from failed strategies, and decision making after uncertain outcomes. On observed state reuse, checkpoint analysis shows that many Gemini 2.5 Flash failures occur before the model observes the state it is later expected to reuse. In a pre-specified 92-seed study, targeted protocol-disambiguation guidance increases state observation from 65.5% under a matched non-guidance control message to 95.4%. Repeating the same design with Gemini 3.7 Flash produces the opposite effect, while state observation no longer reliably predicts task completion. These results show that the dominant source of failure can shift across model generations, motivating evaluation that diagnoses where and why long-horizon security agents fail rather than relying only on aggregate task success.

Wei Shao, Chongzhou Fang, Zuxiong Tan +4

University of California, Davis, USA · Rochester Institute of Technology, USA

Agent Failure AnalysisLong-Horizon Agent EvaluationLong-Horizon LLM AgentsLLM Agent Security
AskPDF