智能体
arxiv.org ·
基于知识的多智能体 LLM 轨迹零重放调试
该论文将多智能体 LLM 系统的长执行轨迹调试建模为基于知识的决策支持问题：把轨迹编译为覆盖路由、记忆、工具调用、不确定性和潜在证据的结构化事件知识图谱，并用轻量预测器 BranchPoint-Latent 在固定预算下预测哪些事件会被反事实重放 oracle 标记为高影响，从而避免线性增长的重放成本。在 37 个轨迹族上校准后，单个 learning-to-rank 梯度提升预测器将留出族的 Branch Recall@5 从 0.73 提升至 0.93，且不消耗 oracle 重放。作者同时刻画了廉价图中心性何时足够、何时需要学习证据，并声明不主张普遍优势。
AI推荐理由 arXiv 论文（cs.SE/cs.AI），提出将多智能体 LLM 执行轨迹调试转化为基于知识图谱的决策支持问题，用 BranchPoint-Latent 预测器在零重放成本下预测反事实高影响事件。摘要给出具体量化结果：在 37 个轨迹族上，留出族 Branch Recall@5 从 0.73 提升到 0.93，并明确说明不主张普遍优势、刻画了廉价图中心性何时足够。局限在于仅基于摘要，未提供代码、数据集规模或独立复现证据，且作者自述不提出新的 replay oracle，效果依赖确定性 replay oracle 的校准。
78
正文
Computer Science > Software Engineering
arXiv:2606.14805 (cs)
[Submitted on 11 Jun 2026 (v1), last revised 26 Sep 2026 (this version, v2)]
Title:Knowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces
Authors:Hyeonjeong Cha, Daein Weon, Dong Ho Kang
View a PDF of the paper titled Knowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces, by Hyeonjeong Cha and 2 other authors
View PDF
HTML (experimental)
Abstract: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.
Comments:
Subjects:
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
ACM classes:
I.2.11; I.2.6; D.2.5
Cite as:
arXiv:2606.14805 [cs.SE]
(or
arXiv:2606.14805v2 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2606.14805
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Dong Ho Kang Dr. [view email]
[v1]
Thu, 11 Jun 2026 22:34:39 UTC (19 KB)
[v2]
Sat, 26 Sep 2026 17:18:32 UTC (19 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Knowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces, by Hyeonjeong Cha and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SE
new
|
recent
| 2026-06
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)