paper-with-me

Papers

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

2026-06-11 · Dong Ho Kang, Hyeonjeong Cha, Daein Weon arxiv

Reliable operation of multi-agent large language model (LLM) systems depends on debugging long execution traces, where the few causally decisive events are buried in unstructured logs of messages, routes, memory writes, and tool calls. The standard tool is counterfactual replay (rewind, edit, and re-run the trajectory to measure each event's effect), but its cost grows linearly with the number of candidate events, making exhaustive replay infeasible at scale. We frame trace debugging as a knowledge-based decision-support problem. Each trace is compiled into a structured event knowledge graph over routing, memory, tool-use, uncertainty, and latent evidence, and a calibrated predictor decides where a scarce replay budget should be spent. We do not propose a new replay oracle; we propose a method to predict its results without paying the replay cost. We formulate zero-replay counterfactual-effect prediction: given a trace under a fixed budget, predict which events the oracle would mark high-effect before any replay is performed. BranchPoint-Latent is a lightweight predictor over observable, structural, uncertainty, and latent features of the knowledge graph. Calibrated against a deterministic replay oracle across 37 trace families, a single learning-to-rank gradient-boosted predictor raises per-trace localization (Branch Recall@5) from 0.73 to 0.93 on held-out families at zero oracle-replay cost. Rather than claiming universal dominance, we characterize when cheap graph centrality suffices and when learned evidence is necessary. The result is an auditable, cost-efficient decision-support system for AI-reliability debugging, positioned explicitly on the cost-accuracy frontier with reproducible artifacts.

📄 PDF Abstract BibTeX arXiv:2606.14805

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

2026-07-21 · Kunlun Zhu, Xuyan Ye, Zhiguang Han, Yuchen Zhao 외 hf

LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but provide little support for identifying the …

BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge

2026-05-15 · Sihan Fu, Oucheng Liu, Shiyuan Wang, Jin Shi 외 arxiv

Code agents increasingly help developers work with unfamiliar repositories, but every such task depends on a costly prerequisite: bootstrapping the repository into a usable development state. This process requires substa…

Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents

2026-04-30 · Mehmet Iscan arxiv

Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved memory is useful only…

ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systems

2024-08-05 · Andrew Zhu, Liam Dugan, Chris Callison-Burch

Recently, there has been increasing interest in using Large Language Models (LLMs) to construct complex multi-agent systems to perform tasks such as compiling literature reviews, drafting consumer reports, and planning v…

AI Agent

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

2026-08-26 · Zhongwen Luan, Xiaoyu Zhang, Ming Hu, Yue Yang 외 arxiv

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 …