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

arXiv:2608.23616 · cs.SE, cs.AI · Submitted 2026-08-22 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-08-22

Updated: 2026-09-20

Code: https://github.com/Parker-Fawcett/rebuild-dossier

Terminology

• Ablation — 21× in this paper · explained in 1 episode
• Verification — 20× in this paper · explained in 2 episodes
• Fidelity — 11× in this paper · explained in 2 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Ablation study — 4× in this paper · explained in 1 episode
• Trace — 4× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Scaffolding — 3× in this paper · explained in 3 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Human-in-the-Loop — 2× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 2 episodes

Sources

• AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs
• SWE-Bench+: Enhanced Coding Benchmark for LLMs
• Concrete Problems in AI Safety
• Guidelines for Empirical Studies in Software Engineering involving Large Language Models
• UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench

Related papers

• Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
• GitSkills: A Dataset of Agent Skills on GitHub
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
• IntentCoding: Amplifying User Intent in Code Generation
• Incentives and Outcomes in Bug Bounties