自动化智能体组合：基于背包问题的智能体组件选择方法

Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection

October 18, 2025

作者: Michelle Yuan, Khushbu Pahwa, Shuaichen Chang, Mustafa Kaba, Jiarong Jiang, Xiaofei Ma, Yi Zhang, Monica Sunkara

cs.AI

摘要

设计高效的智能体系统需要在动态且不确定的环境中无缝组合和集成智能体、工具及模型。现有方法大多依赖静态的语义检索技术来发现工具或智能体。然而，由于能力描述的不完整和检索方法的局限性，现有组件的有效复用与组合仍面临挑战。组件选择的问题在于决策未基于能力、成本和实时效用。为解决这些难题，我们引入了一种受背包问题启发的结构化、自动化智能体系统组合框架。该框架使组合智能体能够系统性地识别、选择并组装最优的智能体组件集合，同时兼顾性能、预算限制和兼容性。通过动态测试候选组件并实时建模其效用，我们的方法简化了智能体系统的组装过程，促进了资源的可扩展复用。使用Claude 3.5 Sonnet在五个基准数据集上的实证评估表明，基于在线背包的组合器始终位于帕累托前沿，与基线相比，在显著降低组件成本的同时实现了更高的成功率。在单智能体设置中，在线背包组合器的成功率相比检索基线提升了高达31.6%。在多智能体系统中，当从包含100多个智能体的库中选择时，在线背包组合器将成功率从37%提升至87%。这一显著的性能差距证实了我们的方法在不同领域和预算约束下的强大适应性。

English

Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods rely on static, semantic retrieval approaches for tool or agent discovery. However, effective reuse and composition of existing components remain challenging due to incomplete capability descriptions and the limitations of retrieval methods. Component selection suffers because the decisions are not based on capability, cost, and real-time utility. To address these challenges, we introduce a structured, automated framework for agentic system composition that is inspired by the knapsack problem. Our framework enables a composer agent to systematically identify, select, and assemble an optimal set of agentic components by jointly considering performance, budget constraints, and compatibility. By dynamically testing candidate components and modeling their utility in real-time, our approach streamlines the assembly of agentic systems and facilitates scalable reuse of resources. Empirical evaluation with Claude 3.5 Sonnet across five benchmarking datasets shows that our online-knapsack-based composer consistently lies on the Pareto frontier, achieving higher success rates at significantly lower component costs compared to our baselines. In the single-agent setup, the online knapsack composer shows a success rate improvement of up to 31.6% in comparison to the retrieval baselines. In multi-agent systems, the online knapsack composer increases success rate from 37% to 87% when agents are selected from an agent inventory of 100+ agents. The substantial performance gap confirms the robust adaptability of our method across diverse domains and budget constraints.