Haochen Liu, Qianhao Zhu, Zixuan Wang, Dingming Li, Tongbo Chen, Peng Qiu, Yingqi Qu, Weiming Lu (Zhejiang University) · Decision Model Teachers

Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents

The paper studies whether a decision model that acts poorly can still be a good teacher for LLM agents. It compares three decision models and three general LLMs as actors and judges on ALFWorld, and uses JEV as a teacher for GRPO training. JEV raises a Qwen2.5-1.5B policy from 72.8% to 82.9% success on ALFWorld and from 56.8% to 71.4% on WebShop. Code is available at github.com/ZJU-REAL/decision-agents.

Open the source ↗

Similar Research & Safety releases

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.