Commit History

Автор SHA1 Съобщение Дата
  Boxuan Li 6f235937cf Evaluation time travel: allow evaluation on a specific version (#2356) преди 1 година
  Xingyao Wang 01ef90205d Add CodeActSWEAgent to remove browsing & github + improvements on agentskills (#2105) преди 1 година
  Xingyao Wang 5114230e53 Some SWE-Bench infer fixes and improvements (#2065) преди 1 година
  Xingyao Wang 602ffcdffb Implement `agentskills` for OpenDevin to helpfully improve edit AND including more useful tools/skills (#1941) преди 1 година
  Boxuan Li b845a38169 Small improvements & fixes to SWE-Bench (#1874) преди 1 година
  Xingyao Wang b2fdb963b6 Add detailed tutorial for adding new evaluation benchmarks (#1827) преди 1 година
  Xingyao Wang e31f8b8322 automatically get agent version for eval (#1844) преди 1 година
  Xingyao Wang 2406b901df feat(SWE-Bench environment) integrate SWE-Bench sandbox (#1468) преди 1 година