SOURCE-LINKED INTELLIGENCE

EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Open-ended reinforcement learning often relies on rubric-based rewards for tasks without directly verifiable answers. Yet the policy and reward system form a dynamic feedback loop: as the policy optimizes the current reward, an initially useful reward system may become unreliable due to reward hacking or reduced response discriminability. The reward system should therefore evolve rather than remain fixed during training. Existing dynamic-rubric methods adapt evaluation criteria, but reward failures can also arise from scoring mechanisms or signal composition. We introduce EvoRS, a self-evolvin

Read original source ↗ Open in workspace

recordType

paper

region

Global