超越文档：编译上下文与受控 Agent 打造可交付工作成果
Beyond the Document: Compiled Context and Governed Agents for Any Work Product
AI 导读
论文提出可移植 Agent 格式（PAF）包，将工作成果连同编译上下文、证据、来源与交互规则一起交付。在 4 个新包、400 个冻结问题和 12,000 条评估响应上，托管受控读取器成功率 96%，高于指令加原始文件检索的 86%（Holm 校正 p < 10^-7）；0.8B 参数离线读取器整体成功率 69%，错误或越权回答率 2.9%，远低于仅用原始文件的 56%。
正文 · 原文
Abstract:A document preserves the visible result of professional work but often discards the research, calculations, assumptions, evidence, and authorization boundaries behind it. We study a different unit of delivery: a Portable Agent Format (PAF) package that carries a work product together with compiled context, evidence, provenance, and rules for subsequent interaction. To test whether this context remains useful beyond the process that produced it, we evaluate four new packages, created after the hosted and offline readers were fixed: an investment proposal, fund research, financial-statement analysis, and an engineering incident review. Two packages were produced by specialized agents and two through a general-purpose assistant's packaging skill. Across 400 frozen questions and 12,000 evaluated responses, a hosted governed reader succeeds on 96% of questions versus 86% with instructions plus raw-file retrieval (Holm-adjusted p < 10^-7). On the 260 answerable questions per condition, success is 94% versus 79%; the gap varies by package. Source-material chat and instructions alone reach 48% and 74% overall. A separate 0.8-billion-parameter offline reader succeeds on 69% overall, but 54% on answerable questions. Its -1 response rate is 2.9%, combining materially wrong and unauthorized answers, versus 56% with the source and instructions alone. Ablations suggest advantages for the integrated selector and package-adapted writer, without isolating representation from training effects. The same run exposes a failure: offline retrieval resolves none of the 40 historical-record questions in one financial-data package. These findings support treating compiled knowledge as part of the delivered work product, while leaving independent standards interoperability and end-to-end governance conformance unproven.
| Comments: | 8 pages, 1 figure, 4-package held-out evaluation; 12,000 evaluated responses |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2611.13055 [cs.SE] |
| (or arXiv:2611.13055v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13055 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: James Rhodes [view email]
[v1]
Mon, 9 Nov 2026 15:20:00 UTC (18 KB)
来源：arXiv cs.AI · arxiv.org