让角色可执行：从团队轨迹自动提炼出能指导行为的智能角色
ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models
- 基于团队轨迹学习未来感知的角色原型，实现行为可预测
- 在两个问答数据集上比单智能体提升13.5~16.1点指标
- 角色能捕捉可迁移的行为专长，适合多智能体协作研究
角色为语言模型智能体提供了可解释的组织接口，但现有系统将角色视为与学习行为和参数更新无关的手写提示标签。我们提出，有效角色应是可执行的控制变量：能总结对未来效用有预测性的行为，引导后续交互，并识别负责该行为的可训练能力。为此，我们提出ExRole框架，从前缀局部团队轨迹中学习未来感知的角色原型，将其解析为可读指令和对齐的标记，还可按轮次分配共享的LoRA秩槽。在MuSiQue和2WikiMultiHopQA两个基准上，ExRole相比单智能体搜索分别提升15.0/14.4和13.5/16.1 EM/F1点；相较于最强非ExRole基线，仍保持11.5/11.6和7.7/9.7点提升。所有实验结果一致表明，由轨迹生成的角色条件优于无角色、人工、随机和打乱角色的替代方案。角色-智能体-轮次干预分析显示，所诱导角色捕捉到了超越固定身份或轮次位置的可迁移行为专长。
原文摘要 · Abstract (English)
Roles provide an interpretable interface for organizing language-model agents, yet most multi-agent systems treat them as hand-written prompt labels disconnected from learned behavior and parameter updates. We argue that a useful role should instead be an executable control variable: it should summarize behavior predictive of future utility, guide subsequent interaction, and identify the trainable capacity responsible for that behavior. We introduce ExRole, a trajectory-to-role framework that learns future-aware role prototypes from prefix-local team traces, resolves them into readable instructions and token-aligned role markers, and optionally routes shared LoRA rank slots with turn-aligned credit. Across MuSiQue and 2WikiMultiHopQA, ExRole improves over single-agent search by 15.0/14.4 and 13.5/16.1 EM/F1 points, respectively. Against the strongest non-ExRole controls, the corresponding gains remain 11.5/11.6 and 7.7/9.7 points. Across both benchmarks, the controlled results consistently favor trajectory-induced role conditioning over role-free, manual, random, and shuffled alternatives. Role-Agent-Turn interventions further show that the induced roles capture transferable behavioral specialization beyond fixed agent identities or turn positions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。