Signals 4 · free daily AI digest

Chronicle: Cut-Point Replay for Regression Testing of LLM Agents

Paper recorded by Signals 4 on 2026-09-17 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-17 on arXiv · recorded by Signals 4 on 2026-09-18

Category: cs.CL · 自然语言处理 · first seen 2026-09-18

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 chan

Read on arXiv →

#7 most recent of 186 cs.CL papers we have recorded · ↑ newer: UniPolicy: Unified Objective-Specific Policies for Generative Search A · ↓ older: What Does Privileged Information Add to On-Policy Self-Distillation?
Cite this page: Chronicle: Cut-Point Replay for Regression Testing of LLM Agents: the #7 most recent of 186 cs.CL papers we have recorded (as of 2026-09-17). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/chronicle-cut-point-replay-for-regression-testing-of-llm-agents.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions