REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces

• URL: http://arxiv.org/abs/2606.09071v1
• Date: Mon, 08 Jun 2026 06:11:57 GMT
• Title: REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
• Abstract summary: Large language model (LLM) agents solve complex tasks through long plan-and-execution traces, yet the ability to locate errors in a completed traces still lags far behind.<n>We propose methodname, a method that closes this gap by diagnosing a candidate error step, testing it through controlled replay with a diagnosis-specific patch, and using the verified outcome flip as contrastive evidence to refine the final attribution.
• Score: 10.98846592145896
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet the ability to locate errors in a completed traces still lags far behind, especially in the \emph{silent failure} regime. Existing approaches predict suspect steps via classifiers or LLM judges, or recover correct answers via retry, but none feed the intervention outcome back to \emph{refine the attribution itself}. We propose \methodname, a method that closes this gap by diagnosing a candidate error step, testing it through controlled replay with a diagnosis-specific patch, and using the verified outcome flip as contrastive evidence to refine the final attribution. Across four localization benchmarks spanning multi-hop reasoning across domains, \methodname achieves the highest localization accuracy among same-auditor methods across all four benchmarks, with the largest gains on structured tool-use traces, while providing actionable localization even when ground-truth answers are unavailable.

Related papers

• TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories [48.638067300108276]
  Critical error detection aims to locate the earliest error step in a failed trajectory that is responsible for the final failure.<n>Long trajectories make it difficult to identify individual errors, since the evidence for judging a step may be scattered across distant instructions, observations, and prior context.<n>We propose Traj Debug, an error-lifecycle tracing framework that addresses long-trajectory error discovery.
  arXiv  Detail & Related papers  (2026-08-06T17:51:20Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents [14.988334585821939]
  Coding agents are ranked almost entirely by resolve rate.<n>A single pass/fail label says nothing about why a run failed or why an accepted run spent extra steps, time, or tokens.<n>We present TraceProbe, a trajectory-diagnostic framework that recovers what resolve rate hides.
  arXiv  Detail & Related papers  (2026-07-07T12:09:46Z)
• StepFinder: A Temporal Semantic Framework for Failure Attribution in Multi-Agent Systems [11.500948775496218]
  Failure attribution is a task that aims to automatically identify the root cause step responsible for a failure.<n>Existing failure attribution methods mainly rely on LLMs to reason over original execution trajectories.<n>We propose StepFinder, a lightweight failure attribution framework.
  arXiv  Detail & Related papers  (2026-06-02T10:45:49Z)
• Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories [51.22051230894794]
  Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable.<n>We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through expert review.<n>We propose DRIFT, a claim-centric auditing framework that tracks agent claims, checks their support in trajectory evidence, and marks spans where unsupported or conflicting claims affect the answer path.
  arXiv  Detail & Related papers  (2026-06-01T10:50:26Z)
• Self-Healing Agentic Orchestrators for Reliable Tool-Augmented Large Language Model Systems [0.10210859604701106]
  Self-healing agentic orchestrator treats reliability as a runtime bounded control problem.<n>Self-healing achieves 98.8% task success, compared with 94.5% for retry-only and 93.8% for full replanning.
  arXiv  Detail & Related papers  (2026-05-31T19:27:22Z)
• Early Diagnosis of Wasted Computation in Multi-Agent LLM Systems via Failure-Aware Observability [8.036549927091286]
  This paper introduces a failure-aware observability framework for diagnosing wasted computation in multi-agent LLM traces.<n>We instantiate the framework in a three- agent question-answering system and evaluate it on 165 GAIA validation traces under identical execution caps.
  arXiv  Detail & Related papers  (2026-05-31T17:50:11Z)
• ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling [57.42714978834704]
  ExComm is a communication protocol for exploration-stage agentic test-time scaling.<n>We show that ExComm consistently outperforms strong test-time scaling baselines.
  arXiv  Detail & Related papers  (2026-05-21T07:38:44Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• Towards Self-Improving Error Diagnosis in Multi-Agent Systems [31.04613892300063]
  We introduce ErrorProbe, a self-improving framework for semantic failure attribution.<n>ErrorProbe identifies responsible agents and the originating error step.<n>It maintains a verified episodic memory that updates only when error patterns are confirmed by executable evidence.
  arXiv  Detail & Related papers  (2026-04-19T23:13:05Z)
• Runtime Execution Traces Guided Automated Program Repair with Multi-Agent Debate [8.424102114588559]
  Automated Program Repair (APR) struggles with complex logic errors and silent failures.<n>Current LLM-based APR methods are mostly static, relying on source code and basic test outputs.<n>We propose TraceRepair, a multi-agent framework that leverages runtime facts as shared constraints for patch validation.
  arXiv  Detail & Related papers  (2026-04-03T02:23:25Z)
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems [48.971606069204825]
  DoVer is an intervention-driven debug framework for large language model (LLM)-based multi-agent systems.<n>It augments hypothesis generation with active verification through targeted interventions.<n>DoVer flips 18-28% of failed trials into successes, achieves up to 16% milestone progress, and validates or refutes 30-60% of failure hypotheses.
  arXiv  Detail & Related papers  (2025-12-07T09:23:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.