# Role-Agent：通过双角色进化自举LLM智能体

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-09 22:28
- AIHOT 分数：55
- AIHOT 链接：https://aihot.virxact.com/items/cmq7pt5at00jxslepyquf2bm4
- 原文链接：https://arxiv.org/abs/2606.10917

## AI 摘要

Role-Agent框架让单个大语言模型同时充当智能体和环境，实现自举式共同进化。包含两个组件：World-In-Agent（WIA）让LLM作为智能体并在每次动作后预测下一状态，将预测与实际状态的对齐作为过程奖励，激励环境感知推理；Agent-In-World（AIW）则从失败轨迹中分析失败模式，并检索具有相似失败模式的任务，重塑训练数据分布进行针对性练习。在多个基准测试上，Role-Agent平均比强基线提升超过4%。

## 正文

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, 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.