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~~

接口在下游:设计人机协作的条款

The Interface Is Downstream: Designing the Terms of Human-Agent Collaboration

Hector Ouilhet Olmos

arXiv 2609.28801首次发表:更新:

AI 中文总结

本文基于个人智能体Alicia的溯源失败,提出拟人环境概念,通过审计注意力、证据、行动和学习,强调将协作接口从下游输出转向上游的纠正、同意与学习。

AI 中文摘要

在智能体做出响应或采取行动之前,大部分体验已被设计完成。记忆与检索塑造了它注意到的内容。证据规则塑造了它可以声称的内容。权限塑造了它可以执行的操作。学习规则塑造了它带入下一次交互的内容。这一论点来自Alicia,一个我自2026年1月起构建并使用的个人智能体。一次微调试点未产生可辩护的模型性能结果。它暴露了一个溯源失败:Alicia重复了来自检索综合的解读,引用了该综合所标注的来源笔记,却将综合本身排除在可见链条之外。在对三十三条引用的模型盲审中,一位评审者判定,在十六条中继引用中,检索到的中介提供了主张,在四条中提供了部分主张。十二条直接检索目标的引用中,有五条缺乏评审所提供目标摘录中的支持。这些判定尚未裁定,且数据包未公开。我将这种共享环境称为拟人环境:一种将人类实践转化为软件的持久计算环境。第一篇拟人论文翻译了伙伴关系。本文翻译了工作室,即实践发生的房间。该失败促使对注意力、证据、行动和学习的审计,并为每项提供了审查工件和可用补救措施。测试在于个人能否检查和质疑塑造队友行为的内容。输出在下游。纠正、同意和学习将协作接口带回上游。

英文摘要

Before an agent responds or acts, much of the experience has already been designed. Memory and retrieval shape what it notices. Evidence rules shape what it may claim. Permissions shape what it can do. Learning rules shape what it carries into the next encounter. The argument comes from Alicia, a personal agent I've built and used since January 2026. A fine-tuning pilot produced no defensible model-performance result. It exposed a provenance failure: Alicia repeated an interpretation from a retrieved synthesis, cited a source note credited by that synthesis, and left the synthesis out of the visible chain. In a model-blind review of thirty-three citations, one reviewer judged that the retrieved intermediary supplied the claim in sixteen relayed citations and part of it in four. Five of twelve citations to directly retrieved targets lacked support in the target excerpt supplied for review. These judgments remain unadjudicated, and the packet is not public. I call the shared setting a humorphic environment: a persistent computational setting that translates a human practice into software. The first Humorphism paper translated partnership. This paper translates the studio, the room where practice happens. The failure prompted an audit of attention, evidence, action, and learning, with a review artifact and available recourse for each. The test is whether the person can inspect and contest what shaped the teammate's behavior. The output is downstream. Correction, consent, and learning carry the collaborative interface back upstream.

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑