Knowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces

arXiv:2606.14805 · cs.SE, cs.AI · Submitted 2026-06-11 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-06-11

Updated: 2026-09-26

Terminology

• Trace — 116× in this paper · explained in 2 episodes
• Accuracy — 18× in this paper · explained in 1 episode
• Knowledge Graph — 13× in this paper · explained in 7 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Calibration — 11× in this paper · explained in 7 episodes
• LLM judge — 7× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Multi-Agent System — 4× in this paper · explained in 6 episodes
• Feature Extraction — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• External Validation — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Interactive Debugging and Steering of Multi-Agent AI Systems
• WhatIf: Interactive Exploration of LLM-Powered Social Simulations for Policy Reasoning
• DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
• Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
• TRAIL: Trace Reasoning and Agentic Issue Localization
• Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems
• MASPrism: Lightweight Failure Attribution for Multi-Agent Systems Using Prefill-Stage Signals
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• ReAct: Synergizing Reasoning and Acting in Language Models
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Generative Agents: Interactive Simulacra of Human Behavior
• CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
• Training Verifiers to Solve Math Word Problems
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties