Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Wanghan Xu, Shuo Li, Tianlin Ye, Qinglong Cao, Yixin Chen, Hengjian Gao, Yiheng Wang, Qi Li, Kun Li, Sheng Xu, Shengdu Chai, Fangchen Yu, Xiangyu Zhao, Zhangrui Zhao, Weijie Ma, Zijie Guo, Koutian Wu, Haoyu Zhou, Haoxiang Yin, Lixue Cheng, Chaofan Hu, Haoxuan Li, Lu Mi, Xuxuan Xie, Yifan Zhou, Ruizhe Chen, Zhiwang Zhou, Xingjian Guo, Yuhao Zhou, Xuming He, Shengyuan Xu, Xinyu Gu, Jiamin Wu, Mianxin Liu, Chunfeng Song, Fenghua Ling, Dongzhan Zhou, Shixiang Tang, Yuqiang Li, Mao Su, Peng Ye, Siqi Sun, Bin Wang, Xue Yang, Zhenfei Yin, Tianfan Fu, Guangtao Zhai, Wanli Ouyang, Bo Zhang, Lei Bai, Wenlong Zhang · May 28, 2026 · Citations: 0

Coding Law Rubric Rating
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Moderate trust

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Moderate

Derived from extracted protocol signals and abstract evidence.

Abstract

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • The abstract does not clearly describe the evaluation setup.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

Background context only.

Main weakness

The abstract does not clearly describe the evaluation setup.

Trust level

Moderate

Usefulness score

50/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Weak / implicit signal

Usefulness for eval research

Moderate-confidence candidate

Extraction confidence 55%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Rubric Rating

Directly usable for protocol triage.

"AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify."

Quality Controls

missing

Not reported

No explicit QC controls found.

"AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify."

Benchmarks / Datasets

strong

Researchclawbench

Useful for quick benchmark comparison.

"We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify."

Rater Population

strong

Domain Experts

Helpful for staffing comparability.

"Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery."

Human Feedback Details

  • Uses human feedback: Yes
  • Feedback types: Rubric Rating
  • Rater population: Domain Experts
  • Unit of annotation: Multi Dim Rubric
  • Expertise required: Coding

Evaluation Details

  • Evaluation modes:
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Moderate
  • Use this page as: Secondary protocol comparison source

Protocol And Measurement Signals

Benchmarks / Datasets

Researchclawbench

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Metadata summary

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify.
  • We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains.
  • Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Research Summary

Contribution Summary

  • AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify.
  • We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains.
  • We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness.

Why It Matters For Eval

  • We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains.
  • We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness.

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Rubric Rating

  • Gap: Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Pass: Benchmark or dataset anchors are present

    Detected: Researchclawbench

  • Gap: Metric reporting is present

    No metric terms extracted.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.