SOURCE-LINKED INTELLIGENCE

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

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

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, se

Read original source ↗ Open in workspace

recordType

paper

region

Global