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

• URL: http://arxiv.org/abs/2605.02651v1
• Date: Mon, 04 May 2026 14:34:36 GMT
• Title: ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review
• Abstract summary: Agentic Reproducibility Assessment (ARA) formalizes assessment as a structured reasoning task over scientific documents.<n>Given a paper, ARA extracts a directed graph linking sources, methods, experiments, and outputs, then evaluates its reconstructability.<n>ARA achieves 61% accuracy on three benchmarks, and the highest accuracy reported on ReproBench and GoldStandardDB.
• Score: 10.258519605411772
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Ontology-Guided Multi-Agent Extraction of Evaluation Objects from Academic Review Texts: Evidence from Chinese Library and Information Science [6.306930443447107]
  This study proposes an ontology-guided multi-agent framework for evaluation object extraction.<n>It achieves a Precision of 90.33%, Recall of 84.55%, Entity-level F1 of 87.34%, Strict Typed F1 of 79.78%, and Type Accuracy of 91.35%.
  arXiv  Detail & Related papers  (2026-08-30T03:09:47Z)
• From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent [52.42081442204093]
  We argue that a key limitation is the lack of flexibility to proactively investigate suspicious parts of a paper.<n>We propose ProReviewer, a scientific peer review agent that proactively reviews a paper guided by a maintained, structured review log.<n> Experiments show that ProReviewer with an 8B backbone, trained by supervised fine-tuning and optimized by reinforcement learning, achieves the highest average score across five quality dimensions.
  arXiv  Detail & Related papers  (2026-06-11T13:38:23Z)
• An Agentic Approach Towards Replication Package Quality Evaluation [1.6950215926321557]
  This paper explores an agentic approach for assessing replication package quality.<n>We consolidate 380 requirements from 34 sources into 51 criteria, of which 31 are operationalized for automated artifact-based evaluation.<n>Preliminary evaluation on five replication packages shows high inter-run consistency of 91.4% and 75.4% correctness.
  arXiv  Detail & Related papers  (2026-06-01T10:00:41Z)
• PaperRepro: Automated Computational Reproducibility Assessment for Social Science Papers [33.12402746591649]
  PaperRepro is a novel two-stage, multi-agent approach for automated assessment.<n>In the execution stage, agents execute the reproduction package and edit the code to capture reproduced results as explicit artifacts.<n>In the evaluation stage, agents evaluate agents using explicit evidence.
  arXiv  Detail & Related papers  (2026-02-10T09:04:59Z)
• The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research [56.80927148740585]
  We address the challenges of scalability and rigor by flipping the dynamic and developing AI agents as research evaluators.<n>We use mechanistic interpretability research as a testbed, build standardized research output, and develop MechEvalAgent.<n>Our work demonstrates the potential of AI agents to transform research evaluation and pave the way for rigorous scientific practices.
  arXiv  Detail & Related papers  (2026-02-05T19:00:02Z)
• Assessing Reproducibility in Evolutionary Computation: A Case Study using Human- and LLM-based Assessment [2.0365636651755263]
  We study the practices in papers published in the Combinatorial Optimization and Metaheuristics track of the Evolutionary Computation Conference over a ten-year period.<n>We introduce a structured checklist and apply it through a systematic manual assessment of the selected corpus.<n>In addition, we propose RECAP (REproducibility Checklist Automation Pipeline), an automated system that automatically evaluates signals from paper text and associated code.
  arXiv  Detail & Related papers  (2026-02-05T08:32:29Z)
• Beyond "Not Novel Enough": Enriching Scholarly Critique with LLM-Assisted Feedback [81.0031690510116]
  We present a structured approach for automated novelty evaluation that models expert reviewer behavior through three stages.<n>Our method is informed by a large scale analysis of human written novelty reviews.<n> Evaluated on 182 ICLR 2025 submissions, the approach achieves 86.5% alignment with human reasoning and 75.3% agreement on novelty conclusions.
  arXiv  Detail & Related papers  (2025-08-14T16:18:37Z)
• ReviewRL: Towards Automated Scientific Review with RL [16.43785996852824]
  Existing automated review approaches struggle with factual accuracy, rating consistency, and analytical depth.<n>We introduce ReviewRL, a reinforcement learning framework for generating comprehensive and factually grounded scientific paper reviews.<n>Our approach combines: (1) an ArXiv-MCP retrieval-augmented context generation pipeline that incorporates relevant scientific literature, (2) supervised fine-tuning that establishes foundational reviewing capabilities, and (3) a reinforcement learning procedure with a composite reward function.
  arXiv  Detail & Related papers  (2025-08-14T03:26:13Z)
• QRA++: Quantified Reproducibility Assessment for Common Types of Results in Natural Language Processing [6.653947064461629]
  We present QRA++, a quantitative approach to assessment that produces continuous-valued degree of assessments at three levels of granularity.<n>We illustrate this by applying QRA++ to three example sets of comparable experiments.
  arXiv  Detail & Related papers  (2025-05-13T13:04:04Z)
• Position: AI Evaluation Should Learn from How We Test Humans [65.36614996495983]
  We argue that psychometrics, a theory originating in the 20th century for human assessment, could be a powerful solution to the challenges in today's AI evaluations.
  arXiv  Detail & Related papers  (2023-06-18T09:54:33Z)
• Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP [84.08476873280644]
  Just 13% of papers had (i) sufficiently low barriers to reproduction, and (ii) enough obtainable information, to be considered for reproduction. As a result, we had to change our coordinated study design from a reproduce approach to a standardise-then-reproduce-twice approach.
  arXiv  Detail & Related papers  (2023-05-02T17:46:12Z)
• Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation [136.16507050034755]
  Existing human evaluation studies for summarization either exhibit a low inter-annotator agreement or have insufficient scale. We propose a modified summarization salience protocol, Atomic Content Units (ACUs), which is based on fine-grained semantic units. We curate the Robust Summarization Evaluation (RoSE) benchmark, a large human evaluation dataset consisting of 22,000 summary-level annotations over 28 top-performing systems.
  arXiv  Detail & Related papers  (2022-12-15T17:26:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.