Skip to main content
Search

Xin Yin

1 related articles

Subscribe to updates
  1. arXiv

    Code agents learn to read a repository's pull-request history, lifting SWE-Bench Verified resolution from 69.2% to 72.9%

    Code agents solving repository-level tasks usually read only the current source tree, leaving the design decisions and compatibility constraints recorded in merged pull requests unused. Chronos distills each merged pull request into a structured experience card and links the cards in a typed graph of code, developer-intent and organizational relations, then retrieves by semantic entry plus weighted multi-hop expansion. On SWE-Bench Verified the full workflow improves SWE-Agent on all six evaluated backbones, raising mean resolution from 69.2% to 72.9% and reaching 79.8% in the strongest configuration.

You’re all caught up