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

arXiv: https://arxiv.org/abs/2606.07591 · HTML: https://mlsanity.com/paper/2606.07591/

## Key facts

- Cited by 17 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 23 of its 57 references that are in the map.
- First posted on arXiv 28 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, 23 of 23)

- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark](https://mlsanity.com/paper/2409.11363/) (2024)
- [AI-Researcher: Autonomous Scientific Innovation](https://mlsanity.com/paper/2505.18705/) (2025)
- [EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery](https://mlsanity.com/paper/2603.08127/) (2026)
- [AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents](https://mlsanity.com/paper/2602.06855/) (2026)
- [AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage](https://mlsanity.com/paper/2505.20662/) (2025)
- [Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows](https://mlsanity.com/paper/2512.16969/) (2025)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration](https://mlsanity.com/paper/2605.03042/) (2026)
- [MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs](https://mlsanity.com/paper/2505.20740/) (2025)
- [ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning](https://mlsanity.com/paper/2511.14366/) (2025)
- [SciDataCopilot: An Agentic Data Preparation Framework for AGI-driven Scientific Discovery](https://mlsanity.com/paper/2602.09132/) (2026)
- [Domain Specific Benchmarks for Evaluating Multimodal Large Language Models](https://mlsanity.com/paper/2506.12958/) (2025)

## Built on by (most cited first, 17 of 17)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks](https://mlsanity.com/paper/2608.14905/) (2026)
- [Intern-S2-Preview: Scientific Agentic Foundation Model](https://mlsanity.com/paper/2608.13505/) (2026)
- [ASI-Bench: At the Dawn of Artificial Superintelligence](https://mlsanity.com/paper/2608.17271/) (2026)
- [AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities](https://mlsanity.com/paper/2607.13705/) (2026)
- [BrainPilot: Automating Brain Discovery with Agentic Research](https://mlsanity.com/paper/2607.15079/) (2026)
- [TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents](https://mlsanity.com/paper/2609.05079/) (2026)
- [Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation](https://mlsanity.com/paper/2607.08758/) (2026)
- [Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search](https://mlsanity.com/paper/2608.15669/) (2026)
- [SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?](https://mlsanity.com/paper/2609.09113/) (2026)
- [Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation](https://mlsanity.com/paper/2609.11115/) (2026)
- [Research-Native by Construction: Minimal Nodes, Re-verifiable Workflows, and Compounding Memory for Long-Horizon Scientific Agents](https://mlsanity.com/paper/2609.35182/) (2026)
- [Can AI Scientists Coordinate at Runtime?](https://mlsanity.com/paper/2610.00980/) (2026)
- [ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences](https://mlsanity.com/paper/2610.08691/) (2026)
- [SciExam for ENSO: Can AI Agents Build Climate Models?](https://mlsanity.com/paper/2610.10513/) (2026)
- [ClawLoop: Self-Improving Agents via Harness-Native Training Loop](https://mlsanity.com/paper/2610.14118/) (2026)
- [ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch](https://mlsanity.com/paper/2610.18088/) (2026)

## Abstract (arXiv)

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.