FARS: A Fully Automated Research System Deployed at Scale

2026-06-30

AI Summary

This work proposes the first end-to-end AI-driven scientific research system capable of autonomous, cross-domain operation at scale. Addressing the limitations of existing automated research frameworks—which often rely on manually specified topics or are confined to narrow tasks—the system employs a language model–powered multi-agent architecture coupled with a shared workspace to orchestrate the full research lifecycle, from topic selection and experimental design to execution and paper writing. Deployed across 67 fine-grained AI/ML topics, it generated 166 complete manuscripts and constructed an auditable, full-cycle research corpus. Expert evaluation of 282 reviews confirms that a subset of outputs demonstrates scholarly merit, while also exposing critical challenges in current automated science, including narrow experimental scope, methodological constraints, and concerns regarding academic integrity.

Abstract

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.

Problem

• automated research system
• large-scale deployment
• AI-for-AI research
• scientific reproducibility
• research integrity

Innovation

• automated research system
• language-model agents
• shared workspace
• large-scale deployment
• auditable research corpus