Chronos Enables Code Agents to Reason over Software Evolution
- Published
- Source
- arXiv
- Paper number
- 1198
- Field
- Software Engineering
- arXiv ID
- 2610.11578
Key points
- Chronos distilled merged pull requests into experience cards with four fields: Summary, Signals, Motivation, and Solution.
- It built an evolution graph connecting the cards through eleven typed relations of code continuity, developer intent, and organizational context.
- Semantic search located entry cards and weighted multi-hop expansion retrieved connected history for the agent to selectively read.
- On SWE-Bench Verified it improved SWE-Agent across all six LLM backbones, raising the mean resolution rate from 69.2% to 72.9% and reaching 79.8% with MiniMax M2.5.
- With the same backbone it raised resolution rates from 48.3% to 51.7% on SWE-Bench Pro and from 41.0% to 43.5% on FEA-Bench Lite.
- In a human evaluation on 100 tasks, graph-grounded retrieval increased the mean useful cards from 1.24 to 2.87 and the fraction of tasks receiving useful experience from 68% to 89%.
Paper links
External research summaries. These are not HDATF publications or measured product results.