⌁ Awesome Auto Research Hub Papers · Datasets · Projects
中文 GitHub
← Back to papers

FARS: A Fully Automated Research System Deployed at Scale

arXiv 2026 65.8 method, system, application

TLDR

FARS is a fully automated AI research system that produced 166 papers across 67 topics, evaluated by 282 structured reviews.

Reasoning

The paper presents a large-scale deployment of an automated research system with auditable artifacts and reviewer evaluations, demonstrating both strengths in scalability and weaknesses in experimental scope and integrity. However, the abstract lacks details on methodology and limitations beyond high-level failure modes.

Read-first score

Read-first score 65.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 82.

Recency 8%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=experiment,result

Topical relevance 42%
68.3

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Reproducibility 25%
46

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=artifact,code

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 39.

Keyword Scores

automated research
10
research automation
10
automated scientific discovery
9
AI for scientific research
9
AI scientist
8
scientific discovery agent
8
autonomous research agent
7
paper writing agent
7
automated experimentation
6
experiment design agent
5
literature review agent
2
survey generation
1

Deep Analysis

Innovations

  • Fully automated AI-for-AI research system operating across diverse topics at scale without human framing or pre-defined tasks
  • Stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts
  • Large-scale public deployment producing 166 complete research papers on 67 fine-grained AI/ML topics
  • Preservation of intermediate artifacts as an auditable corpus rather than a curated set of successes

Methodology

FARS uses stage-specific agents for ideation, planning, experimentation, and writing, coordinated via a shared workspace that captures all artifacts. The system was deployed to generate 166 papers across 67 AI/ML topics, and evaluated with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure.

Key Results

Reviews indicate FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment, while also exposing recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.

Limitations

  • Narrow experimental scope in generated research
  • Methodological limitations in the produced papers
  • Integrity issues detected in some artifacts

Resources

Paper

Tags