训练AI时多监督一个东西，探索能力反而更强
训练AI智能体时，标准做法只让模型预测自己的动作，环境反馈只当背景信息。这篇论文发现，如果同时让模型预测环境接下来会发生什么——即使它实际部署时根本不需要这个能力——后续强化学习的效果会更好。在多个基准上，这种训练方式让AI在相同采样预算下解决更多任务，且最终策略更接近初始状态、保留更多探索空间。原因在于：只监督动作会让模型逐渐丧失对后果的预测能力，而联合监督防止了这种偏科。它不是你明天能用上的东西，但提示了一个反直觉的方向：让AI学一些它用不到的东西，反而能让它更聪明。
📄 原文摘要(英文)
Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment observations as context but not as prediction targets. We ask whether this convention provides the best initialization for subsequent reinforcement learning. We introduce ActObs, which also supervises the observation tokens already present in each trajectory. Although deployed agents never generate observations, learning to predict them encourages the policy to model action consequences without adding data, parameters, sequence tokens, or forward passes. The methods perform similarly after SFT but diverge after GRPO. On Qwen3-4B, GRPO from ActObs achieves higher pass@k at every evaluated sampling budget than its action-only counterpart on Terminal-Bench 2.0. On Qwen3-8B, it trades some pass@1 reliability for higher pass@k (+3.4 pp at pass@16) and solves more distinct tasks. The advantage extends to cross-domain code editing on aider-polyglot (+4.2 pp at pass@1 at 4B), whose tasks are unseen during SFT and RL. ActObs retains more entropy during RL while requiring less policy movement, leaving the final policy closer to its SFT initialization. Our analysis traces this difference to SFT: action and observation gradients rapidly become orthogonal, while action-only training leaves a large residual observation gradient and degrades environment prediction below the base model. Joint supervision prevents this one-sided specialization, preserving consequence prediction and preparing the policy for downstream exploration.