Search papers, labs, and topics across Lattice.
This paper introduces DeepRepro, a state-aware framework designed to enhance the reproduction of machine learning papers into functional code by addressing the challenges posed by evolving repository states. By utilizing execution-state-aware subplanning, DeepRepro dynamically adapts to changes in dependencies and execution feedback, ensuring that the planning process remains aligned with ongoing execution. Experimental results demonstrate that DeepRepro significantly outperforms existing code generation systems, highlighting its effectiveness in managing long-horizon reproduction tasks.
DeepRepro outperforms traditional code generation methods by dynamically adapting to evolving repository states, ensuring consistent and functional reproduction of ML papers.
Recent advances in agentic large language models (LLMs) have enabled increasingly autonomous software engineering workflows, yet automatic machine learning (ML) paper-to-code reproduction remains a challenging long-horizon problem. Unlike conventional code generation, this task requires constructing and maintaining a fully functional repository whose state continuously evolves during execution. Existing systems typically rely on static upfront planning followed by sequential file-level generation, which often leads to inconsistencies as dependencies, interfaces, and execution feedback change over time. We propose DeepRepro, a state-aware framework for paper-to-code reproduction based on execution-state-aware subplanning. DeepRepro dynamically transforms evolving repository states and runtime feedback into fine-grained implementation subplans, keeping planning aligned with execution throughout repository construction. The framework further incorporates repository-aware orchestration and a lightweight process-aware interface for transparent monitoring of long-horizon reproduction. Experiments on PaperBench Code-Dev show that DeepRepro consistently outperforms strong scientific and commercial code-agent baselines.
