Commit Graph

5 Commits (c31f66525d6700305675b27f7c98aa9b3041eb9d)

Author SHA1 Message Date
RileyChen23 65def67cee feat: add code agent model service runner 2026-07-12 17:53:02 +08:00
RileyChen23 125b49dfc1 feat: integrate verifiable rewards into GRPO 2026-07-12 17:47:36 +08:00
RileyChen23 bfb5a1261b feat: add execution-feedback repair agent 2026-07-12 17:42:52 +08:00
RileyChen23 07643d5f05 feat: add pass-at-k code evaluation 2026-07-12 17:38:20 +08:00
RileyChen23 8e06fb6d52 feat: add code execution verifier and rewards 2026-07-12 17:29:07 +08:00