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

arXiv: https://arxiv.org/abs/2603.01801 · HTML: https://mlsanity.com/paper/2603.01801/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 10 of 10)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [The Distracting Effect: Understanding Irrelevant Passages in RAG](https://mlsanity.com/paper/2505.06914/) (2025)
- [AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage](https://mlsanity.com/paper/2505.20662/) (2025)
- [Plan-over-Graph: Towards Parallelable LLM Agent Schedule](https://mlsanity.com/paper/2502.14563/) (2025)

## Built on by (most cited first, 6 of 6)

- [The Last Human-Written Paper: Agent-Native Research Artifacts](https://mlsanity.com/paper/2604.24658/) (2026)
- [TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing](https://mlsanity.com/paper/2604.03143/) (2026)
- [CoACT: Action-Preserving Observation Compression for Coding Agents](https://mlsanity.com/paper/2607.02911/) (2026)
- [To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation](https://mlsanity.com/paper/2603.15159/) (2026)
- [Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code](https://mlsanity.com/paper/2606.11817/) (2026)
- [RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?](https://mlsanity.com/paper/2609.28850/) (2026)

## 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.