Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL paradigm that utilizes hindsight generative self-evaluation as dense reward signals while simultaneously calibrating them against the environmental feedbacks. Empirically, MISE enables an agent to learn autonomously from dense internal rewards supplementing sparse extrinsic signals. Theoretically, our work provides the first formal foundation for the paradigm of generative self-rewarding. We prove that utilizing hindsight self-evaluation rewards is equivalent to minimizing an objective that combines mutual info...
| Authors | Jiashu Yao, Heyan Huang, Zeming Liu et al. |
|---|---|
| Primary category | cs.CL |
| Published | 13 April 2026 |
| Last updated at source | 13 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.