FARS: A Fully Automated Research System Deployed at Scale

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Qiong Tang, Xiangkun Hu, Xiangyang Liu, Yiran Chen, Yunfan Shao
• Venue: arXiv: cs.AI
• Published: 2026-06-30
• Collected: 2026-07-01
• URL: http://arxiv.org/abs/2606.31651v1
• PDF: https://arxiv.org/pdf/2606.31651v1
• DOI: UNKNOWN

Plain-Language Brief

FARS is a fully automated AI-for-AI research system that can generate, execute, and write complete research papers on various topics at scale. In its first public deployment, FARS produced 166 research papers across 67 fine-grained AI/ML topics.

What the Document Says

• FARS is a fully automated AI-for-AI research system.
• FARS operates across research topics at scale.
• FARS generates, advances projects through ideation, planning, experimentation, and writing.
• FARS uses stage-specific agents coordinated through a shared workspace.
• FARS preserved intermediate artifacts as an auditable corpus rather than a curated set of successes.
• In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics.
• 282 structured reviews were conducted from volunteer reviewers covering 140 papers.
• The reviews indicate that FARS can produce review-worthy and occasionally strong AI/ML research artifacts.
• The reviews expose recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.

Key Concepts Mentioned

• Fully Automated Research System (FARS)
• AI-for-AI
• research papers
• 67 fine-grained AI/ML topics
• structured reviews

Claims Made by the Document

• FARS can generate, advance, and write complete research papers.
• FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment.

Evidence Used

• The description of FARS' capabilities.
• The number of research papers produced and the topics they cover.
• The number and nature of structured reviews conducted.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Recent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selected examples, human-framed topics, or a few pre-defined research tasks. We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system designed to operate across research topics at scale. FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing, using stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts. In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics while preserving intermediate artifacts as an auditable corpus rather than a curated set of successes. We evaluate this corpus with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure. The reviews indicate that 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.