拓扑搜索要给每个 agent 记学分：Meta CATS，BigCodeBench +5.3 pp、部署 token −54%
拓扑搜索要给每个 agent 记学分：Meta CATS，BigCodeBench +5.3 pp、部署 token −54%
View PDF HTML (experimental) Abstract: An LLM multi-agent system (MAS) is only as good as the agents it chooses to trust: its accuracy and cost hinge on its topology, meaning which agents are included and how they communicate. A single task score, however, does not reveal...
Meta CATS (arXiv:2610.29292)
“View PDF HTML (experimental) Abstract: An LLM multi-agent system (MAS) is only as good as the agents it chooses to trust: its accuracy and c”
Abstract:An LLM multi-agent system (MAS) is only as good as the agents it chooses to trust: its accuracy and cost hinge on its topology, meaning which agents are included and how they communicate. A single task score, however, does not reveal which agents help or hinder performance. We propose Contrastive Attribution Topology Search (CATS), which searches for compact teams within a fixed supergraph of specialized agents. An LLM attributer compares execution traces across candidate topologies and assigns credit to individual agents. CATS uses these credits to update supergraph edges while progressively pruning weak edges and agents, yielding a small team for deployment. With small open-weight models and matched candidate evaluations, CATS improves mean accuracy on BigCodeBench by 5.3 percentage points over score-only heuristic search while using 54$\%$ fewer deployment tokens. On MBPP, CATS matches the strongest baselines with fewer tokens than the other searches. In a HotpotQA prompt-poisoning stress test, CATS excludes all adversarially prompted agents in all three runs, whereas random search retains some at comparable accuracy. Per-agent credit thus supports both team optimization and the pruning of potentially harmful agents.
| Subjects: | Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.29292 [cs.CL] |
| (or arXiv:2610.29292v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29292 arXiv-issued DOI via DataCite |
Submission history
From: Tom Zehle [view email]
[v1]
Wed, 21 Oct 2026 06:46:11 UTC (957 KB)
Source: Agent Control Flash News · arxiv.org
Related Products & Analysis
Cursor Agent 架构全景拆解：从影子工作区到多文件推演引擎
全面剖析 Cursor 在 Agent 模式下的底层技术实现，解析影子分支隔离、LSP 上下文剪枝以及预测性补全的核心架构细节与工程实践经验。
Vercel v0 推出全新多 Agent 协作画布与实时全栈部署预览
动态速评：v0 正在从单一组件生成器演进为全栈应用搭建协作台，尤其是与 Neon/Postgres 的直连极大降低了全栈原型验证成本。