Prompt-Level Reward Specifications for Open-Ended Post-Training 事件

Prompt-Level Reward Specifications for Open-Ended Post-Training arXiv:2605.29275v1 Announce Type: new Abstract: Open-ended post-training benefits from rewards that make prompt-specific success conditions explicit, rather than relying only on post-hoc scalar scores. In instruction following, writing, and decision-support tasks, response quality depends on local requirements, holistic preferences, and explicit constraints, but existing reward methods often leave these criteria implicit or cover o