Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Reveal

• URL: http://arxiv.org/abs/2608.23616v2
• Date: Wed, 26 Aug 2026 01:18:29 GMT
• Title: Rebuild Dossier: Mechanically-Enforced Specs for Agentic App Rebuilds, and What Model-Tier Failures Reveal
• Abstract summary: rebuild-dossier is an open-source tool that locks an application's real interface before any code is written.<n>It enforces one-test-at-a-time building through automated checks, not written instructions alone.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction [57.138342889101345]
  Tencent WorkBuddy Bench is a multi-domain evaluation suite for coding agents.<n>This report documents its construction methodology, scoring protocol, and a cross-model leaderboard.
  arXiv  Detail & Related papers  (2026-07-23T04:34:06Z)
• Setup Complete, Now You Are Compromised: Weaponizing Setup Instructions Against AI Coding Agents [0.0]
  coding agents set up projects by reading documentation and installing the dependencies it lists, without verifying their names, sources, or known vulnerabilities.<n>We present the first systematic evaluation of package-install-time supply-chain attacks delivered through ordinary project-setup documentation.<n>Agents catch blatant typosquats reliably, but plausible separator-confusion names slip through, and how often depends on the harness-model pairing.
  arXiv  Detail & Related papers  (2026-07-16T15:47:19Z)
• From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents [0.24554686192257424]
  Productization adds requirements for source boundaries, entity routing, answer contracts, and reproducible traces.<n>We present a harness-engineering approach that reconstructs this pattern into a traceable, auditable LLM-agent architecture.<n>We instantiate it on a public-data slice of five Korean corporate groups and evaluate three research questions.
  arXiv  Detail & Related papers  (2026-07-09T01:08:33Z)
• Can Code Specify a System Precisely Enough to Formally Verify It? [0.0]
  This paper evaluates both on production software: the payment workflow of an operational restaurant point-of-sale system.<n>The core protocol is correct relative to a hand-built, line-cited model under a precisely stated failure model.<n>A single probe of the production payment sandbox exposed a response-shape divergence that makes an entire recovery ladder unreachable.
  arXiv  Detail & Related papers  (2026-07-06T13:39:00Z)
• PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation [51.92442051257354]
  PairCoder improves essentially every benchmark whose artifact is verifiable, on full official metric suites rather than execution alone.<n>TikZ compile rate up 10 to 30 points on every model, at 2.9 to 9.2 times single model cost.
  arXiv  Detail & Related papers  (2026-07-02T08:36:02Z)
• ClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures [1.0742675209112622]
  We study failure modes as stemming from three mechanisms: underspecification, capability errors, and agent harness errors.<n>We propose ClayBuddy, a harness that molds to user preferences and can be modified by the model in-session to mitigate these errors.
  arXiv  Detail & Related papers  (2026-06-13T18:29:53Z)
• Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories [51.22051230894794]
  Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable.<n>We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through expert review.<n>We propose DRIFT, a claim-centric auditing framework that tracks agent claims, checks their support in trajectory evidence, and marks spans where unsupported or conflicting claims affect the answer path.
  arXiv  Detail & Related papers  (2026-06-01T10:50:26Z)
• ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents [59.626170560327274]
  We present textbfClawForge, a generator-backed benchmark framework for executable command-line categories under state conflict.<n>We instantiate this framework as the ClawForge-Bench (17 scenarios, 6 ability categories)
  arXiv  Detail & Related papers  (2026-05-13T21:34:08Z)
• ProgramBench: Can Language Models Rebuild Programs From Scratch? [59.40748183470308]
  ProgramBench measures the ability of software engineering agents to develop software holisitically.<n>End-to-end behavioral tests are generated via agent-driven fuzzing.<n>Models favor monolithic, single-file implementations that diverge sharply from human-written code.
  arXiv  Detail & Related papers  (2026-05-05T09:17:02Z)
• RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents [0.9821874476902969]
  LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric.<n>This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation pipeline rather than improving the model.<n>We introduce RewardHackingAgents, a workspace-based benchmark that makes two compromise vectors explicit and measurable.
  arXiv  Detail & Related papers  (2026-03-11T22:06:44Z)
• Where LLM Agents Fail and How They can Learn From Failures [62.196870049524364]
  Large Language Model (LLM) agents have shown promise in solving complex, multi-step tasks.<n>They amplify vulnerability to cascading failures, where a single root-cause error propagates through subsequent decisions.<n>Current systems lack a framework that can comprehensively understand agent error in a modular and systemic way.<n>We introduce the AgentErrorTaxonomy, a modular classification of failure modes spanning memory, reflection, planning, action, and system-level operations.
  arXiv  Detail & Related papers  (2025-09-29T18:20:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.