Kilian Lieret(@KLieret):Can LMs discover & fix bugs if you don't tell them what went wrong? To proactively maintain a repo, agents need to find problems before users do. SWE-sweep benchmarks this on 100 repos, 22 languages, 4k real bugs (numpy, php interpreter, lean kernel). Top models get <5%.

Kilian Lieret

@KLieret

Meta Superintelligence, prev. Princeton. SWE-bench multilingual/multimodal, SWE-agent, mini-swe-agent, SWE-smith, CodeClash, ProgramBench

参加 May 2021

282 フォロー中 2.9K ファン

Kilian Lieret@KLieret

2026.10.01 14:47

Can LMs discover & fix bugs if you don't tell them what went wrong? To proactively maintain a repo, agents need to find problems before users do. SWE-sweep benchmarks this on 100 repos, 22 languages, 4k real bugs (numpy, php interpreter, lean kernel). Top models get <5%.