多智能体协作通过技能混合提升动态任务求解能力
SKIMIX: Multi-Agent Harness-Time Scaling with Skill Mixture for Dynamic Harness Engineering
- 不同技能组合的智能体通过迭代优化协同工作
- 六项推理任务中数学开放题表现显著提升，选择题效果有限
- 首次改进后收益最大，智能体数量非单调增长
AI智能体依赖大型技能库，但技能的选择、组合与维护仍具挑战。本文提出SKIMIX，一种多智能体框架，不同技能配置的智能体通过迭代精炼协作。该框架结合基于嵌入的技能检索、子模抗稀释路由和自适应技能演化。在六个推理基准上，多智能体协作显著提升开放式数学推理性能，但在多项选择任务上收益有限甚至为负。智能体数量的扩展呈非单调性，多数改进发生在首轮精炼阶段。结果表明，任务特性决定技能集成是否有效，为可扩展智能体设计提供实践指导。
原文摘要 · Abstract (English)
AI agents increasingly rely on large skill libraries, but selecting, combining, and maintaining skills remains difficult. We propose SKIMIX, a multi-agent framework in which agents with different skill portfolios collaborate through iterative refinement. SKIMIX combines embedding-based skill retrieval, submodular anti-dilution routing, and adaptive skill evolution. Across six reasoning benchmarks, multi-agent collaboration substantially improves open-ended mathematical reasoning but offers limited or negative gains on multiple-choice tasks. Agent-count scaling is non-monotonic, and most improvements arise during the first refinement round. These results show that task characteristics determine whether skill-level ensembles help and provide practical guidance for scalable agent design.
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。