让智能体角色自动进化，同时保证系统结构不被破坏。
Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning
- 通过约束性编辑机制动态调整角色池，保持系统结构完整。
- 在三个大模型上测试，任务得分提升且角色演化稳定。
- 适合需要长期运行、角色可变的多智能体推理系统。
基于角色的大型语言模型多智能体系统需要可适应的角色池，但调整此类系统不仅仅是提示优化问题：角色常带有结构性义务，包括能力覆盖、消息兼容性、验证机制、最终答案聚合及解析器兼容输出协议。现有系统要么固定角色池失去适应性，要么允许无约束生成导致角色漂移，破坏必要角色和答案契约。本文提出契约保持的角色演化框架，要求每项修改必须维持五类结构性契约（能力、通信、验证、聚合、输出协议）。我们实现该框架为SERO（自演化角色编排），通过信用引导检索、信用排序通信有向图、受保护的终端聚合器与条件验证修复机制，结合上下文带权控制器，仅当修改满足契约且提升任务得分时才提交。在三种大模型基座上的真实世界推理基准测试中，验证了契约保持角色演化的有效性。
原文摘要 · Abstract (English)
Role-based LLM multi-agent systems need adaptive role pools, yet adapting such systems is not merely a matter of prompt optimization: roles often carry structural obligations, including capability coverage, message compatibility, validation, final-answer aggregation, and parser-compatible output protocols. Existing systems either fix the role inventory and lose adaptivity, or allow unconstrained generation to induce role drift, removing structurally necessary roles and breaking answer contracts. We formulate this as contract-preserving role evolution, requiring every committed edit to preserve five structural contracts (capability, communication, validation, aggregation, output protocol). We instantiate this formulation in SERO, a Self-Evolving Role Orchestration framework that evolves a typed role-card pool through credit-guided retrieval, a credit-ranked communication DAG with a protected terminal aggregator and conditional validator repair, and a contextual-bandit controller whose LLM-proposed edits are committed only when they preserve the contracts and improve task score. Experiments on real-world reasoning benchmarks across three LLM backbones confirm the value of contract-preserving role evolution.
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。