The Agentic Scientist, 코딩 에이전트를 조율해 자동 과학 연구 수행
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
- 매체
- arXiv
- 게시
- 중요도
- 2/5
- 화제 지수
- 5
한국어 요약
연구자가 코딩 에이전트와 함께 계산 연구를 진행할 수 있도록 설계된 end-to-end 분산 파이프라인이다. 작업 초안 작성부터 아이디어 생성, 기획, 실험, 분석, 기준 구성, 리포트 작성까지 각 단계를 코딩 에이전트와 메타 컨트롤러가 조율한다. 개발 버전으로 ALIFE 2026에 게재된 연구 논문 1건을 제출했으며, 기계학습 미해결 문제에 자동 적용해 다양한 계산 연구 도메인에서 과학적 발견을 입증했다.
원문 발췌 · English
Modern coding agents are fundamentally reshaping the role of human input for computational research: they write code, launch in silico experiments, analyze their results, and autonomously operate with ever-increasing time horizons. Despite these developments, fully autonomous research agents suffer from a limited ideation radius and myopic hill-climbing search dynamics. To bridge this gap, we introduce The Agentic Scientist, an end-to-end distributed pipeline for human researchers to conduct computational research alongside modern coding agents. Building on its predecessor, our system decomposes research into task drafting, idea generation, planning, sandboxed experimentation, result aggregation, baseline and ablation construction, post-hoc analysis, and report writing. Importantly, each step in the pipeline is powered by the next generation of coding agents and leverages agentic self-verification. The overall research process is driven by a meta-controller that manages parallel research agents and enforces rubric verification at each stage. This design enables the same orchestration layer to be reused across heterogeneous domains with different execution environments, agentic coding harnesses, and evaluation metrics. Our system can be used across a spectrum of autonomy: either as a co-scientist tool or to perform end-to-end scientific investigation. Within the co-scientist setting, we leveraged a development version of our system to submit a single research paper, which got accepted for publication at ALIFE 2026. We further apply The Agentic Scientist fully autonomously to open problem-solving tasks in machine learning, and demonstrate the system's capability of scientific discovery across different domains of computational research. Our ablations suggest that reliable scientific autonomy depends not only on base model capabilities, but also on the cross-agent orchestration layer.