mlsanityData to 7 Oct 2026

What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction

arXiv 2603.01801 ↗First posted 2 Mar 2026cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Automated paper reproduction -- generating executable code from academic papers -- is bottlenecked not by information retrieval but by the tacit knowledge that papers inevitably leave implicit. We formalize this challenge as the progressive recovery of three types of tacit knowledge -- relational, somatic, and collective -- and propose method, a graph-based agent framework with a dedicated mechanism for each: node-level relation-aware aggregation recovers relational knowledge by analyzing implementation-unit-level reuse and adaptation relationships between the target paper and its citation neighbors; execution-feedback refinement recovers somatic knowledge through iterative debugging driven by runtime signals; and graph-level knowledge induction distills collective knowledge from clusters of papers sharing similar implementations. On an extended ReproduceBench spanning 3 domains, 10 tasks, and 40 recent papers, method achieves an average performance gap of 10.04% against official implementations, improving over the strongest baseline by 24.68%. The code will be publicly released upon acceptance; the repository link will be provided in the final version.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 10 of its 38 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

10 of 38 references.

References · 10

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  4. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  5. 2025PaperBench: Evaluating AI's Ability to Replicate AI Researchcited by 286
  6. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repaircited by 225
  7. 2025Paper2Code: Automating Code Generation from Scientific Papers in Machine Learningcited by 67
  8. 2025The Distracting Effect: Understanding Irrelevant Passages in RAGcited by 32
  9. 2025AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineagecited by 29
  10. 2025Plan-over-Graph: Towards Parallelable LLM Agent Schedulecited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026The Last Human-Written Paper: Agent-Native Research Artifactscited by 12
  2. 2026TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharingcited by 8
  3. 2026CoACT: Action-Preserving Observation Compression for Coding Agentscited by 4
  4. 2026To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generationcited by 3
  5. 2026Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Codecited by 0
  6. 2026RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?cited by 0