让大模型自己造工具，减少重复计算，提升系统速度与可靠性。
Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems
- 提前编译重复流程为可验证的工具，代替每次请求重写代码。
- 实测降低50%延迟42%，错误率最高下降53%，并减少运行波动。
- 适合追求高可靠、低延迟的工业级大模型应用团队。
生产环境中的大模型代理常因每次请求重复生成代码而浪费延迟和可靠性。本文提出一种代理工具自生成流水线，将重复的标准化操作流程（SOP）步骤在部署前编译为已验证、带版本的工具。工具生成器通过收集执行痕迹、观察后端数据模式与取值，生成候选工具并基于标注案例进行修复。运行时，代理直接调用工具，仅在必要时回退至代码生成。我们在一个包含44个节点的异构指标后端告警诊断系统中部署该方案。实测显示，工具调用使中位延迟降低42%；在1500条历史告警上，通过抑制重复步骤的运行波动，端到端错误率最高降低53%。由于工具返回紧凑结构化结果，还可支持更简单的直调架构，在消融实验中进一步降低中位延迟62%。版本化工具也增强了可审计性，暴露出规范缺口与上游数据漂移问题。结果表明，能自主构建与维护工具库的大模型代理——即自演化代理的核心能力——可显著提升工业级大模型系统的速度、可靠性与可运维性。
原文摘要 · Abstract (English)
Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that agents that build and maintain their own tool libraries, a key element of self-evolving agents, can make industrial LLM systems faster, more reliable, and easier to operate.
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。