AI快讯 / AI 开源项目

self-evolve

Methodology skill + deterministic harness for agents that self-iterate any skill/repo/project. Anti-self-deception by design — an un-gameable acceptance gate so 'accepted = real improvement', not a fake score-up curve. Built for the open-ended, no-ground-truth domains the self-improving-agent literature skips. 521 tests.

原文来源AI 开源 Releases
查看官方原文

Methodology skill + deterministic harness for agents that self-iterate any skill/repo/project. Anti-self-deception by design — an un-gameable acceptance gate so 'accepted = real improvement', not a fake score-up curve. Built for the open-ended, no-ground-truth domains the self-improving-agent literature skips. 521 tests.