AI RESEARCH
Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents
arXiv CS.LG
•
ArXi:2604.16335v1 Announce Type: new Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable terminal rewards such as whether all unit tests pass. While these binary signals reflect whether the final solution is correct, they provide little guidance for shaping intermediate behaviors during multi-step interactions, thereby limiting improvements in the overall quality of the resolution process. To address this, we.