# Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection arXiv: https://arxiv.org/abs/2510.16499 ยท HTML: https://mlsanity.com/paper/2510.16499/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. - Builds on 21 of its 42 references that are in the map. - First posted on arXiv 18 Oct 2025. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 21 of 21) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023) - [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023) - [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020) - [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023) - [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023) - [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024) - [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024) - [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024) - [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023) - [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024) - [Multi-agent Architecture Search via Agentic Supernet](https://mlsanity.com/paper/2502.04180/) (2025) - [Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2410.02506/) (2024) - [Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence](https://mlsanity.com/paper/2407.07061/) (2024) - [AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning](https://mlsanity.com/paper/2406.11200/) (2024) - [Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2503.01763/) (2025) - [RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.03275/) (2025) - [Distributed Constraint Optimization Problems and Applications: A Survey](https://mlsanity.com/paper/1602.06347/) (2016) - [Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications](https://mlsanity.com/paper/2412.05449/) (2024) - [ToolFuzz -- Automated Agent Tool Testing](https://mlsanity.com/paper/2503.04479/) (2025) - [Time Fairness in Online Knapsack Problems](https://mlsanity.com/paper/2305.13293/) (2023) ## Built on by (most cited first, 10 of 10) - [Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts](https://mlsanity.com/paper/2604.00901/) (2026) - [MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition](https://mlsanity.com/paper/2606.00708/) (2026) - [Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees](https://mlsanity.com/paper/2608.19993/) (2026) - [AgentSearchBench: A Benchmark for AI Agent Search in the Wild](https://mlsanity.com/paper/2604.22436/) (2026) - [SkillSelect-Serve: QoS-Aware Budgeted Skill Service Recommendation for LLM Agents](https://mlsanity.com/paper/2607.00011/) (2026) - [n-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models](https://mlsanity.com/paper/2602.09173/) (2026) - [How Much Does Correctness Cost? Budgeted Placement of Strong Correctors in a Weak Multi-Agent Swarm](https://mlsanity.com/paper/2607.09765/) (2026) - [Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and Applications](https://mlsanity.com/paper/2609.07254/) (2026) - [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026) - [Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization](https://mlsanity.com/paper/2610.01017/) (2026) ## Abstract (arXiv) 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.