arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

TRACE:可审计的智能体承诺的操作推理模式

TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments

Edward Y. Chang, Emily J. Chang

arXiv 2607.12480首次发表:更新:

发表机构

Stanford University; Quadrivium AI(斯坦福大学; 四元数人工智能)

机构由 AI 辅助整理,请以论文原文为准。

AI 中文总结

本文提出TRACE模式用于记录推理轨迹,通过字段和测试应对推理不在语言模型中的问题,给出参考程序和操作规范,借助记录-消费者契约形成操作接口,通过示例展示应用,贡献了模式及其契约。

AI 中文摘要

本文定义了TRACE(类型化推理与承诺证据),这是一种用于记录推理轨迹的类型化、版本化模式,以及针对该模式编写记录的参考程序和一种操作规范,即无记录则无持久状态变化。文章分三层论证推理不在语言模型中。该模式通过字段和测试来应对这一缺失,包括TraceRecord及其因果特化、八阶段参考编写器、门优先测量机制、TRACE-Bench协议以及消费者、内存接纳、计划门控、时间遗憾和裁决重用等,更可审计的决策是记录的衡量标准。记录-消费者契约规定了记录的保证和消费者的回报义务,使该模式成为一个操作接口而非被动文档。文中给出两个示例,一个是音乐课程论证,另一个是洪水搜救场景,展示了该模式的应用。附录包含完整模式、编写器算法和成本模型、临床和政策示例、基准协议、收敛指标及使用场景。

英文摘要

This paper defines TRACE (Typed Reasoning And Commitment Evidence): a typed, versioned schema for recording reasoning traces, a reference procedure for writing records against it, and one operating discipline, no durable state change without a record. The paper argues in three layers that reasoning is not in the language model: the autoregressive mechanism natively computes association; chain-of-thought and reinforcement learning inherit its limits; and the formal constructs of reasoning theory, from Socratic procedure to Pearl's ladder, are absent as machinery. The schema answers the absence with fields and tests: the TraceRecord and its causal specialization, an eight-stage reference writer, a gate-first measurement regime, the TRACE-Bench protocol, and the consumers, memory admission, plan gating, temporal regret, and verdict reuse, whose more auditable decisions are the measure of the record. A record-consumer contract states what a record guarantees and what a consumer must honor in return, making the schema an operational interface rather than a passive document. Two worked examples run in the main text: a music-lessons argument traced from sentence to typed verdict, separating association, intervention, and prescription; and a flood search-and-rescue vignette in which a predictive world model reports confident plan success that its own support and out-of-distribution scores contradict, so the record defers the commitment, requests a bounded observation, revises append-only, and clears a different branch. The vignette is illustrative, not empirical; closed-loop evaluation is left to future work, so the contribution is the schema and its contract, not a performance claim. Appendices carry the full schema, writer algorithms and cost model, clinical and policy illustrations, the benchmark protocol, convergence metrics, and usage scenarios.

Comments46 pages, 18 tables, 4 figures

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑