A persistent implementation contract, not a longer plan, is what stops paper-to-code agents losing the spec mid-trajectory
ReproAgent (arXiv 2608.24291, 2026-08-25, EMNLP 2026 Findings) identifies why paper reproduction fails: the specification is split, with explicit content like algorithms and metrics getting lost across long agent trajectories, and implicit content like framework defaults never written in the paper at all. Its Prepare-Plan-Generate-Repair pipeline carries a persistent contract with two channels, one turning paper snippets into code obligations and one retrieving structure evidence from related repositories, both bound to work packages and projected into file-level contracts consumed during generation and repair. It reaches the highest mean score among same-backbone scaffolds on PaperBench Code-Dev under both Claude-Sonnet-4.5 and Gemini-3-Flash. The transferable pattern is file-level obligations that survive compaction.
↳ Follow the thread