RF-Agent: Automated Reward Function Design via Language Agent Tree Search

NeurIPSSpotlight2025

Authors
Ning Gao, Xiuhui Zhang, Xingyu Jiang, Mukang You, Mohan Zhang, Yue Deng
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Designing efficient reward functions for low-level control tasks is a challenging problem…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

efficient control agent

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive