How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks — AI benchmark

Yanlin Fei, Nazhou Liu, Xinmiao Yu, Shaolong Chen, Lei Li, Rahul Thapa, Madalina Ciobanu, Qingqing Mao, Ritankar Das/How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research TasksUnknown

AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landscape; a single system can now carry whole-stage research from an initial hypothesis all the way to final published paper, which is a paradigm now referred to as AutoResearch. Existing evaluations reveal little about how these agents operate or where they break down. Tasks are narrowly-scoped, evaluation measures performance but not process, and failure diagnoses lack systematic coverage or artifact-level visibility. To address this gap, we introduce AutoResearchEval, featuring 100 tasks grounded in published frontier science across 7 scientific domains and the full research lifecycle, including ideation, retrieval, execution, analysis, writing, and review. Evaluating 8 harness-model combinations yields 800 autoresearch agent trajectories, with process-level annotation. We organize these insights into AutoResearch Failure Taxonomy or ARFT, a framework of 45 empirically-grounded failure patterns. To enable scalable fine-grained attribution, we leverage a human-calibrated agent-as-a-judge pipeline to inspect complete trajectories and intermediate artifacts. Failure patterns converge on a single overarching limitation, namely that current agents lack a metacognitive loop, which entails the ability to check what they produced against what they found, revise when it does not hold up, and question whether the path they took was sound. The same patterns recur across all 8 harness-model combinations, including the strongest models tested, locating the deficit at the model level rather than in any particular scaffold; whether orchestration-level interventions can close it is an open question this work does not test. We publicly release AutoResearchEval and ARFT to facilitate continued research and development in autonomous scientific discovery.

benchmark

Stars0

Forks0

HF Downloads—30d

Last commit—

Refreshed7h ago

Project healthUnknownNo activity data.

Production readinessResearch / EarlyBest for exploration and prototyping.

Risk notesUnknown licenseVerify license before production use.

AgentHub Score

55 / 100

Composite score from 6 signals. How we score →

Active project

55Score

Growth

40C

Activity

30C

Documentation

70C+

Maturity

45C

Community

42C

Production

58C

GitHub stars · 3 days observed0 not enough history

snapshots

Repository activity · 3 days observedReal snapshots from pushed_at

inactivepushed

2026-08-212026-08-25

Practical assessment

Should you use it?

✓ Best for

Research and experimentation
Prototype development
Learning agentic patterns

◎ Strengths

Active community
Open source
Well-documented API

✕ Not ideal for

Untested at scale without validation
Teams without AI/ML expertise

⚠ Watch-outs

Review changelog before updating
Verify license for commercial use

Technical details

What's inside

Language—

License—

Sourcearxiv

Open source✗ No

Commercial use—

Docs—

Demo—

PaperarXiv ↗

AgentHub Score

Score 55/100

Below average

Alternatives

RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems

0 · benchmark

Personalized Privacy Control in LLMs via Attention Head Intervention

0 · benchmark

From Natural Language Policies to Executable Obligations: A Verification Harness for Dependable In-Car LLM Agents

0 · benchmark

Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection

0 · benchmark

55 Compare all →

Recent activity

Latest commit ——

Indexed by AgentHub crawler7h ago

Monitor for new releasesongoing