AI学会从失败中提炼“事后经验”，自己教自己
大模型做复杂任务时，常常是做完一整件事（比如订机票）才知道结果对错，中间每一步有没有走偏，没人告诉它。这篇论文让AI自己从做过的任务里提炼“事后经验”——比如“当用户说“便宜点的”，应该先查价格排序再推荐”，然后把这种经验变成训练信号，在下次做类似任务时提前纠正自己。实验显示，这种自我蒸馏方法在文本和视觉任务上都显著提升了成功率，且能泛化到没见过的场景。它不是你明天就能直接用的工具，但指向了一个方向：AI不再只靠人类给反馈，而是学会从自己的行为中复盘、改进。
📄 原文摘要(英文)
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model. SEED first fine-tunes the policy to analyze completed trajectories and generate natural-language skills that capture reusable workflows, decisive observations, or failure-avoidance rules. During RL, the current policy both collects trajectories and serves as the analyzer that extracts hindsight skills from them. Policy updates therefore improve subsequent decision making and skill analysis together, allowing hindsight supervision to evolve with the policy. SEED then re-scores the sampled actions under ordinary and skill-augmented contexts, converting the skill-induced probability shift into a dense token-level on-policy distillation signal. This signal is jointly optimized with outcome-based RL, keeping the auxiliary supervision aligned with the current trajectory distribution. Extensive experiments on text-based and vision-based agentic tasks show that SEED consistently improves performance and sample efficiency, exhibiting robust generalization to unseen scenarios. Our code is available at https://github.com/jinyangwu/SEED.