Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

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

Wanghan Xu, Shuo Li, Tianlin Ye, Qinglong Cao +47 more

Published

May 28, 2026

Citations

0

Trust level

Moderate

Usefulness score

50/100 (Medium)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Domain Experts

Signals refreshed

Jul 2, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Coding Law Rubric Rating

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.

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

Best use

Secondary protocol comparison source

Use if you need

Background context only.

What to verify

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

Main weakness

The abstract does not clearly describe the evaluation setup.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Weak or implicit
Validate from full paper
Usefulness for eval research
50/100
Moderate-confidence candidate

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

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

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.

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."

Benchmarks and datasets

Researchclawbench

Reported metrics

No metric terms were extracted from the available abstract.

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

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.

Recommended queries

Expert verification evaluation

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

  • Human feedback protocol is explicit

    Detected: Rubric Rating

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: Researchclawbench

  • Metric reporting is present

    No metric terms extracted.