自演化多智能体系统的拓扑一致性
Topological Coherence for Self-evolving Multi-agent Systems
浏览论文内容
中文总结 AI 辅助
针对复杂任务中智能体职责、交接与内存边界需与任务依赖保持一致的问题，提出拓扑一致多智能体系统TOCOMAS，通过结构约束与奖励评估的自演化，在多个基准上提升任务成功率。
中文摘要 AI 辅助
复杂任务本质上将工作流结构、智能体职责、协作和内存访问耦合在一起：任务区域界定了职责和工具范围，跨区域依赖产生了交接，所有权边界界定了私有和选择性共享的内存。现有方法可以联合优化智能体和通信结构，但这种优化本身并不要求职责、交接和内存边界与任务依赖保持一致。我们将这一要求称为拓扑一致性。我们引入了TOCOMAS，一个拓扑一致的多智能体系统。TOCOMAS将任务图建立在工具接口上，将兼容的任务节点组织成可复用的职责域，并推导出依赖诱导和基于配置文件的协作以及边界调节的内存可见性。在在线自演化过程中，TOCOMAS提出对智能体、协作和内存策略的耦合更改，仅保留那些满足结构约束并提高评估奖励的候选方案用于后续任务。在BBEH、WorkBench、SWE-Bench-Verified和CoMemBench上，TOCOMAS在各种骨干网络上比基线提高了任务成功率。CoMemBench还显示，在验证进展、交接和内存隔离方面，自演化基线有显著提升。
英文摘要
Complex tasks inherently couple workflow structure, agent responsibility, collaboration, and memory access: task regions delimit responsibility and tool scope, cross-region dependencies give rise to handoffs, and ownership boundaries delimit private and selectively shared memory. Existing methods can jointly optimize agent and communication structures, yet such optimization does not by itself require responsibility, handoff, and memory boundaries to remain consistent with task dependencies. We term this requirement topological coherence. We introduce TOCOMAS, a Topology-Coherent Multi-Agent System. TOCOMAS grounds a task graph in tool interfaces, organizes compatible task nodes into reusable responsibility domains, and derives dependency-induced and profile-conditioned collaboration together with boundary-regulated memory visibility. During online self-evolution, TOCOMAS proposes coupled changes to agent, collaboration, and memory policies, retaining for subsequent tasks only candidates that satisfy structural constraints and improve evaluated reward. Across BBEH, WorkBench, SWE-Bench-Verified, and CoMemBench, TOCOMAS improves task success over baselines across backbones. CoMemBench also shows gains over the self-evolving baseline in verified progress, handoffs, and memory isolation.
发表机构
- Towngas（港华燃气）
机构由 AI 辅助整理，请以论文原文为准。
