动态精简指令与工具，让大模型代理更省资源、更少出错。
Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs
- 按步检索最小必要指令和工具子集，动态生成运行时提示。
- 每步上下文令牌减少95%，工具正确路由率提升32%。
- 适合长周期自主代理，显著降低计算成本和延迟。
大型语言模型（LLM）代理在多步运行中常重复加载长系统指令和大型工具目录，导致成本高、错误率上升、延迟增加。本文提出指令-工具检索（ITR），一种RAG变体，每步仅检索最小系统提示片段和最必要的工具子集。ITR动态构建运行时系统提示，并通过置信度门控的回退机制暴露精简工具集。在可控基准测试中，ITR将每步上下文令牌减少95%，工具正确路由率相对提升32%，端到端任务成本降低70%。该优化使代理在上下文限制内可执行2至20倍更多的循环。收益随步骤数累积，对长周期自主代理尤为关键。本文详述方法、评估协议、消融实验及部署建议。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents often run for many steps while re-ingesting long system instructions and large tool catalogs each turn. This increases cost, agent derailment probability, latency, and tool-selection errors. We propose Instruction-Tool Retrieval (ITR), a RAG variant that retrieves, per step, only the minimal system-prompt fragments and the smallest necessary subset of tools. ITR composes a dynamic runtime system prompt and exposes a narrowed toolset with confidence-gated fallbacks. Using a controlled benchmark with internally consistent numbers, ITR reduces per-step context tokens by 95%, improves correct tool routing by 32% relative, and cuts end-to-end episode cost by 70% versus a monolithic baseline. These savings enable agents to run 2-20x more loops within context limits. Savings compound with the number of agent steps, making ITR particularly valuable for long-running autonomous agents. We detail the method, evaluation protocol, ablations, and operational guidance for practical deployment.
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。