Problem
Research questions and friction points this paper is trying to address.
paper-to-code reproduction
evolving repositories
state-aware
long-horizon problem
execution feedback
DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving Repositories
🤖 AI Summary
为了解决自动机器学习论文到代码的复现问题，提出DeepRepro框架，通过执行状态感知子规划动态调整演化仓库的状态，保持计划与执行的一致性。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
state-aware
subplanning
execution-state-aware
repository-aware orchestration
process-aware interface
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
