DeFA: Dependency-Guided Failure Attribution for LLM Agents
cs.AI
Submitted: 2026-10-01
Updated: 2026-10-01
Comments: DeFA: Dependency-Guided Failure Attribution for LLM Agents
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
- CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
- Why Do Multi-Agent LLM Systems Fail?
- TRAIL: Trace Reasoning and Agentic Issue Localization
- EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
- REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
- Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
- CockpitHAT: Dependency-Graph-Driven Hierarchical Attribution for Embodied Multi-Agent Cockpits
- Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
- AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems