swe-rm-verifier

【效率与协作】Improve SWE agent RL via execution-free reward models optimized for three metrics beyond TTS: discriminative ability (AUC) and calibration (ECE). Shows TTS alone insufficient—models must distinguish correct/incorrect trajectories and align confidence with actual correctness—improving SWE-Bench Verified by 7-10 points with 30B MoE verifier.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准