提出分步执行框架，减少工具调用次数并提升推理可靠性。
Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents
- 先规划流程再执行，用确定性操作替代反复推理
- 正常情况仅需2次语言模型调用，最坏情况3次
- 在检索和分解类任务上显著优于传统方法
使用外部工具的大语言模型代理通常采用反应式执行，每次观测后重复推理，导致延迟高且易受误差传播影响。本文提出‘先规划再推理’（PTR）框架，通过显式合成工作流，由确定性或受控操作执行，并由验证器评估执行轨迹，仅在原工作流不可靠时才触发修复。整个流程被形式化为一系列操作组合：规划、路由、执行、验证、修复与推理；在有限修复条件下，语言模型调用次数在理想情况下不超过2次，最坏情况为3次。在六个基准测试和四种语言模型上的实验表明，PTR在24种配置中有16种实现配对精确匹配优势。结果表明，该方法在以检索为中心和分解密集型任务中尤为有效，而反应式执行在需要强在线适应的任务中仍更优。
原文摘要 · Abstract (English)
Large language model agents that use external tools are often implemented through reactive execution, in which reasoning is repeatedly recomputed after each observation, increasing latency and sensitivity to error propagation. This work introduces Profile--Then--Reason (PTR), a bounded execution framework for structured tool-augmented reasoning, in which a language model first synthesizes an explicit workflow, deterministic or guarded operators execute that workflow, a verifier evaluates the resulting trace, and repair is invoked only when the original workflow is no longer reliable. A mathematical formulation is developed in which the full pipeline is expressed as a composition of profile, routing, execution, verification, repair, and reasoning operators; under bounded repair, the number of language-model calls is restricted to two in the nominal case and three in the worst case. Experiments against a ReAct baseline on six benchmarks and four language models show that PTR achieves the pairwise exact-match advantage in 16 of 24 configurations. The results indicate that PTR is particularly effective on retrieval-centered and decomposition-heavy tasks, whereas reactive execution remains preferable when success depends on substantial online adaptation.
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。