AgentLTL：一种用于测量、执行和训练使用工具的语言模型代理程序合规性的跟踪验证框架
AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents
AI总结：
介绍基于一阶线性时态逻辑的AgentLTL语言，用于表达代理跟踪的程序规则，产生确定性无评判的合规分数，此框架可用于约束和微调，提升模型合规性与准确性。
摘要：
使用工具的语言模型代理通常通过最终答案正确性或语言模型评判来评估，均未捕捉答案生成过程。在安全关键环境中，过程本身是正确性的一部分。本文引入AgentLTL，一种从一阶线性时态逻辑派生的语言，用于表达代理跟踪的程序规则，产生确定性、无评判的合规分数。在一个跨越排序、分支、迭代和基础的基准上，阻塞和警告约束提高了七个模型中五个模型的合规性。使用相同奖励进行微调在保留模式的准确性和合规性方面分别提高了38和17.5个百分点，包括未见的工具名称别名。这些发现与模型获取程序结构而非记忆表面工具名称和过程一致。
英文摘要：
Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges. Neither captures how an answer was produced. In safety-critical settings, the procedure itself is part of correctness. In this paper, we introduce AgentLTL, a language derived from First-Order Linear Temporal Logic (FO-LTL) that expresses procedural rules over agent traces. It yields a deterministic, judge-free compliance score. In this framework, a single specification drives two usages. The first is harnessing: the constraints score completed traces, or gate tool calls by checking each prefix online, before execution. The second is finetuning: the score serves as a dense reward. On a benchmark spanning ordering, branching, iteration, and grounding, block-and-warn harnessing improves compliance on five of seven models. Finetuning with the same reward yields +38 and +17.5 percentage point gains in accuracy and compliance on held-out patterns, including unseen tool-name aliases. These findings are consistent with the model acquiring procedural structure rather than memorizing surface tool names and procedures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
