# R²E: A multi-role LLM evolutionary framework for automated reward function design

- Source: arXiv cs.RO
- Published: 2026-10-26T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/d02tztzmrq8eu9ta71ygwtuj1
- Original: https://arxiv.org/abs/2610.32439

## Summary

The authors propose R²E, a framework for automated reward function design that uses explicit role specialization to mitigate insufficient exploration and optimization instability in LLM-based reward design. The framework includes a novelty explorer responsible for expanding the search space, a guardian responsible for conservative refinements to improve training stability, and an evolver that recombines high-performing rewards through crossover and mutation, with a dynamic scheduling strategy that gradually shifts the search from broad exploration to focused exploitation. R²E also introduces a global elite pool that retains the best-performing rewards to guide subsequent iterations. Experiments on multiple robotic tasks show the effectiveness of the method.