Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems
cs.AI, cs.SE
Submitted: 2026-08-26
Updated: 2026-08-29
Code: https://github.com/crewAIInc/crewAI
Terminology
Sources
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Why Do Multi-Agent LLM Systems Fail?
- Evaluating Large Language Models Trained on Code
- TRAIL: Trace Reasoning and Agentic Issue Localization
- AgentOps: Enabling Observability of LLM Agents
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
- Execution replay and debugging
- Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes
- Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
- AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation
- Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering 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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection