用元工具优化智能体工作流，减少调用次数并提升成功率
Optimizing Agentic Workflows using Meta-tools
- 将重复的工具调用序列转化为确定性元工具，减少中间推理步骤
- 在两个基准上减少最多11.9%的LLM调用，任务成功率提升4.2个百分点
- 适合关注智能体效率与鲁棒性的开发者和研究者
智能体型AI使大模型能够动态推理、规划并调用工具以解决复杂任务。然而，智能体工作流常需大量迭代推理与工具调用，导致显著的运营成本、端到端延迟以及因幻觉引发的失败。本文提出代理工作流优化（AWO）框架，通过分析现有工作流轨迹，识别重复的工具调用模式，并将其转化为元工具——即确定性的复合工具，将多个代理操作合并为一次调用。元工具跳过不必要的中间大模型推理，降低运营成本并缩短执行路径，从而减少失败。在两个智能体AI基准上的实验表明，AWO最多可减少11.9%的LLM调用，同时任务成功率提升最高达4.2个百分点。
原文摘要 · Abstract (English)
Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense, end-to-end latency and failures due to hallucinations. This work introduces Agent Workflow Optimization (AWO), a framework that identifies and optimizes redundant tool execution patterns to improve the efficiency and robustness of agentic workflows. AWO analyzes existing workflow traces to discover recurring sequences of tool calls and transforms them into meta-tools, which are deterministic, composite tools that bundle multiple agent actions into a single invocation. Meta-tools bypass unnecessary intermediate LLM reasoning steps and reduce operational cost while also shortening execution paths, leading to fewer failures. Experiments on two agentic AI benchmarks show that AWO reduces the number of LLM calls up to 11.9% while also increasing the task success rate by up to 4.2 percent points.
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。