浙大研究：弱模型 JEV 当步骤评分器，可将 Qwen2.5-1.5B 智能体成功率从 72.8% 提升至 82.9%
浙大研究：弱模型也能当教练提升智能体表现
浙江大学论文提出，决策模型 JEV 单独执行 ALFWorld 任务成功率仅 42.9%，但作为步骤评分器可将 Qwen2.5-1.5B 策略的成功率从 72.8% 提升至 82.9%。该方法让评分器在整轮结束后为每个动作打分，并将分数加入 GRPO 训练，替代通常需要逐环境标签或每步 LLM judge 的做法。研究建议按评判录制轨迹的能力而非自身执行能力来挑选步骤评分器。
Rohan Paul· @rohanpaul_ai · X·2026-11-15 02:59· 1 小时前AI 评分44
AI 导读
浙江大学论文提出，本身不擅长任务的决策模型 JEV 单独执行 ALFWorld 任务成功率仅 42.9%，但作为步骤评分器可将 Qwen2.5-1.5B 策略的成功率从 72.8% 提升至 82.9%。
正文 · 原文
AI model that is itself bad at a task can still train another AI to do it well.
New paper shows that a decision model called JEV, an AI model built to pick between options instead of writing text, completes only 42.9% of simulated household tasks on its own, yet by reviewing another AI’s moves afterward it raised that AI’s success from 72.8% to 82.9%.
New Zhejiang University paper shows that an AI model that is bad at a task can still train another AI to do it well, by reviewing each of its moves after the attempt ends.
Agent RL usually rewards only the final outcome, so every step gets the same credit. Scoring each step usually needs per-environment labels or an LLM judge at every action.
They tested decision models, which return a choice with probabilities instead of text, as actors and as step graders on ALFWorld and WebShop. As a grader, the model sees the whole run and scores whether each action helped, and those scores are added to GRPO training.
The decision model JEV completes only 42.9% of ALFWorld tasks when acting. As a grader, it lifts a Qwen2.5-1.5B policy to 82.9% success, up from 72.8% with GRPO outcome rewards alone.
Choose step graders by how well they judge recorded runs, not how well they act, and ask about each action, not the outcome.
来源：Rohan Paul · x.com
来源：RadarAI · aihot.news