做 LLM 智能体训练的团队终于有了一个无需外部环境反馈的自我进化方案——Role-Agent 让模型自己当裁判和教练，平均提效 4%+，值得在复杂任务场景中试试。
Role-Agent 是一种让单个 LLM 同时扮演智能体和环境的框架，通过自举式协同进化提升性能。它包含两个核心组件：World-In-Agent（WIA）让模型在每次行动后预测未来状态，利用预测与实际状态的对齐作为过程奖励，促进环境感知推理；Agent-In-World（AIW）则分析失败轨迹中的模式，并检索具有相似失败模式的任务，重新调整训练数据分布进行针对性练习。在多个基准测试中，Role-Agent 平均提升超过 4%，解决了传统智能体学习依赖低效交互反馈和静态训练环境的问题。
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static training environments, which hinder broader generalization. To address these limitations, this paper introduces Role-Agent, \textcolor{black}{a framework} that harnesses a single LLM to function concurrently as both the agent and the environment, enabling a bootstrapped co-evolution. Role-Agent comprises two synergistic components: World-In-Agent (WIA) and Agent-In-World (AIW). In WIA, the LLM acts as the agent and predicts future states after each action; the alignment between predicted and actual states is then used as a process reward, encouraging environment-aware reasoning. In AIW, the LLM analyzes failure modes from failed trajectories and retrieves tasks with similar failure patterns, thereby reshaping the training data distribution for targeted practice. Experiments on multiple benchmarks show that Role-Agent consistently improves performance, yielding an average gain of over 4\% over strong baselines.