# ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review

arXiv: https://arxiv.org/abs/2605.02651 · HTML: https://mlsanity.com/paper/2605.02651/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 77 references that are in the map.
- First posted on arXiv 4 May 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 20 of 20)

- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Can large language models provide useful feedback on research papers? A large-scale empirical analysis](https://mlsanity.com/paper/2310.01783/) (2023)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [Large language models for automated scholarly paper review: A survey](https://mlsanity.com/paper/2501.10326/) (2025)
- [Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025](https://mlsanity.com/paper/2504.09737/) (2025)
- [AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews](https://mlsanity.com/paper/2408.10365/) (2024)
- [AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents](https://mlsanity.com/paper/2602.06855/) (2026)
- [REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?](https://mlsanity.com/paper/2507.18901/) (2025)
- [LLMs as Meta-Reviewers' Assistants: A Case Study](https://mlsanity.com/paper/2402.15589/) (2024)
- [DeepCode: Open Agentic Coding](https://mlsanity.com/paper/2512.07921/) (2025)
- [From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking](https://mlsanity.com/paper/2506.19724/) (2025)
- [From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review](https://mlsanity.com/paper/2506.11343/) (2025)
- [ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?](https://mlsanity.com/paper/2510.24591/) (2025)
- [Position: The ML Community Must Build an AI-Augmented Peer-Review Ecosystem](https://mlsanity.com/paper/2506.08134/) (2025)
- [ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences](https://mlsanity.com/paper/2602.11354/) (2026)
- [Statistical Methods for Replicability Assessment](https://mlsanity.com/paper/1903.08747/) (2019)
- [Assessing Reproducibility in Evolutionary Computation: A Case Study using Human- and LLM-based Assessment](https://mlsanity.com/paper/2602.07059/) (2026)
- [LLM-Assisted Replication for Quantitative Social Science](https://mlsanity.com/paper/2602.18453/) (2026)

## Built on by (most cited first, 1 of 1)

- [RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?](https://mlsanity.com/paper/2609.28850/) (2026)

## Abstract (arXiv)

Scientific peer review increasingly struggles to assess reproducibility at the scale and complexity of modern research output. Evaluating reproducibility requires reconstructing experimental dependencies, methodological choices, data flows, and result-generating procedures, which often exceeds what human reviewers can provide. Agentic Reproducibility Assessment (ARA) formalizes reproducibility assessment as a structured reasoning task over scientific documents. Given a paper, ARA extracts a directed workflow graph linking sources, methods, experiments, and outputs, then evaluates its reconstructability using structural and content-based scores for reproducibility assessments. Experiments on 213 ReScience C articles - the largest cross-domain benchmark of human-validated computational reproducibility studies considered to date - demonstrate ARA's generalizability and consistent workflow reconstruction and assessment across LLMs, model temperatures, and scientific domains. ARA achieves ~61% accuracy on three benchmarks, and the highest accuracy reported on ReproBench (60.71% vs. 36.84%) and GoldStandardDB (61.68% vs. 43.56%), highlighting its potential to complement human review at scale and enabling next-generation peer review. Code and Data available: https://github.com/AndresLaverdeMarin/agentic_reproducibility_assessment.