Chronos Enables Code Agents to Reason over Software Evolution
We introduce Chronos, a test-time framework that makes this connected history available to large language model (LLM)-based code agents.
ProofPaper ↗
Key points
- Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state.
- Chronos distills merged pull requests into structured experience cards and connects them through a typed graph of code-level, developer-intent, and organizational relations.
- Semantic search identifies entry cards, and weighted multi-hop expansion retrieves connected changes for selective reading.
- The same memory guides candidate generation and patch selection: a patch-focused change agent and a validation-strategy agent each develop a patch, and an evolution steward consults history to select between them.
Sources (1)
- [1]Chronos Enables Code Agents to Reason over Software EvolutionarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 09:31 AM
We introduce Chronos, a test-time framework that makes this connected history available to large language model (LLM)-based code agents.
Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026The State of AI Report 2026
- Oct 8, 2026ConwayResearch/Underdog-Saluki-27B-1.0
- Oct 8, 2026Opera: A Verbal Critic Framework for Long-horizon Coding Agents
- Oct 7, 2026CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution
- Oct 7, 2026Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
- Oct 7, 2026Code Understanding is a Bottleneck for Coding Agents