智能体
arxiv.org ·
Chronicle：面向 LLM 智能体回归测试的切点重放
论文提出 Chronicle，将 LLM 智能体运行在非确定性边界记录为不可变信封，并支持切点重放：从记录中回放选定边界子集，其余边界用新代码实时执行，从而把一次故障记录变成可在 CI 中运行的回归测试。在 6 个记录故障的基准上（模型边界为模拟），记录每次跨越增加 23 微秒（约为假设 300ms 模型调用的 0.008%），完整回放零模型调用且 20 次重复位稳定；切点测试在错误代码上失败、在受保护与良性改动上通过。变异研究中，切点测试能捕获所有放行不安全动作的变异体，而全部打桩的基线一个都未捕获。Chronicle 与基准已公开。
AI推荐理由 arXiv 新论文，提出 Chronicle 切点重放方法，把 LLM 智能体运行在非确定性边界记录为不可变信封，并选择性地从记录回放部分边界、其余用新代码实时执行，从而将一次故障记录转化为可在 CI 中运行的回归测试。摘要给出具体量化结果：记录每次跨越增加 23 微秒（约为假设 300ms 模型调用的 0.008%），完整回放零模型调用且在 20 次重复中位稳定，6 个记录故障的切点测试均能在错误代码上失败、在受保护与良性改动上通过；变异研究中切点测试能捕获所有放行不安全动作的变异体，而全部打桩的基线一个都捕获不到。局限在于基准仅 6 个记录故障且模型边界为模拟，尚未在真实生产智能体上验证。
78
正文
Computer Science > Computation and Language
arXiv:2609.20625 (cs)
[Submitted on 17 Sep 2026]
Title:Chronicle: Cut-Point Replay for Regression Testing of LLM Agents
Authors:Tisha Chawla, Susheem Koul
View a PDF of the paper titled Chronicle: Cut-Point Replay for Regression Testing of LLM Agents, by Tisha Chawla and 1 other authors
View PDF
HTML (experimental)
Abstract:Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitwise reproducible, on tools that read changing state, and on a multi-step trajectory that a re-run rarely repeats. Record-and-replay makes a run reproducible, but existing agent tooling records runs only to trace or score them, not to test a code change against them. We present Chronicle, which records an agent run at its non-deterministic boundaries as immutable envelopes and replays it from the record. Its central operation, cut-point replay, serves a chosen subset of boundaries from the record and executes the complementary subset live with new code, turning a recorded incident into a regression test that runs in continuous integration. On a benchmark of 6 recorded failures with simulated model boundaries, recording adds 23 {\mu}s per crossing (0.008% of an assumed 300 ms model call), full replay issues zero model calls and is bit-stable across 20 repetitions, and cut-point tests fail on faulty code and pass on guarded and benign changes for all 6 incidents. In a mutation study of the guarded tools, cut-point tests catch every mutant that lets the recorded unsafe action through, while a baseline that stubs every boundary, using the same assertion, catches none. Chronicle and the benchmark are publicly available at this https URL.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.20625 [cs.CL]
(or
arXiv:2609.20625v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.20625
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Tisha Chawla [view email]
[v1]
Thu, 17 Sep 2026 16:09:57 UTC (27 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Chronicle: Cut-Point Replay for Regression Testing of LLM Agents, by Tisha Chawla and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-09
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?)