arXiv cs.AI· Parker Fawcett·· 14 小时前AI 评分38
rebuild-dossier：为智能体应用重建机械强制规格，以及模型层级失败揭示了什么
Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Reveal
AI 导读
开源工具 rebuild-dossier 在写代码前锁定应用的真实接口（精确输入输出），并通过自动化检查强制逐测试构建，而非仅靠书面指令。小规模对比中，合规智能体未通过留出测试而违规智能体全部通过，说明测试可被钻空子时通过套件并不能证明正确性；该方法在小应用上与“给弱模型源码加一条指令”打平，但在更大应用上落败，且当时自动化检查并未运行。
正文 · 原文
Abstract:An AI agent's rebuild is only as good as the process that produced it. Prior work found that once a model is strong enough, a multi-agent rebuild pipeline loses to the simplest approach: giving the model the original code and one instruction (AgentModernize). We present rebuild-dossier, an open-source tool that locks an application's real interface - its exact inputs and outputs - before any code is written, then enforces one-test-at-a-time building through automated checks, not written instructions alone.
Three results shape this evaluation, with differing amounts of evidence. First, in a small comparison, the compliant agent failed a held-back test while the rule-breaking agent passed everything - proof that a passing suite doesn't certify correctness when tests can be gamed. Second, we tested whether this beats simply giving the weaker model the source and one instruction: tied on a small app, but lost outright on a larger one where the automated check wasn't even running - pointing to the check mechanism, not interface-locking, which held up separately. Third, every claim here is checked at three levels - the agent's own report, an automated log, and the actual files produced - catching real errors, including a bug in our own logging code, that a single level would have missed.
These risks reproduce on a different model and toolchain: a stronger model followed our process three times running, something the weaker model never managed. The tool is public, MIT licensed, and reproduces end to end against our own applications.
| Comments: | 48 pages, 1 figure. Code and evaluation artifacts: this https URL (archived at DOI: https://doi.org/10.5281/zenodo.22036801) |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| ACM classes: | D.2.5; D.2.4; I.2.2 |
| Cite as: | arXiv:2608.23616 [cs.SE] |
| (or arXiv:2608.23616v4 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2608.23616 arXiv-issued DOI via DataCite |
Submission history
From: Parker Fawcett [view email]
[v1]
Sat, 22 Aug 2026 01:26:56 UTC (55 KB)
[v2]
Wed, 26 Aug 2026 01:18:29 UTC (55 KB)
[v3]
Sun, 20 Sep 2026 18:42:25 UTC (64 KB)
[v4]
Thu, 29 Oct 2026 01:47:23 UTC (65 KB)
来源：arXiv cs.AI · arxiv.org