Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents
Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to distinguish trajectories with substantially different debugging quality. We investigate whether the current policy can judge its own trajectories and u...
Yi-Ran Wu, Andrew Zhao, Yu-Rui Chang et al.
· 0 citations