arXiv cs.CL· Robert Tjarko Lange, Luca Grillotti, Yutaro Yamada, Rujikorn Charakorn, David Ha·· 3 天前AI 评分62
The Agentic Scientist：用编码智能体编排自动化科研发现
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
AI 导读
论文提出 The Agentic Scientist，一个面向人类研究者的端到端分布式流水线，可与现代编码智能体协同开展计算研究。系统把研究拆分为任务起草、想法生成、规划、沙箱实验、结果聚合、基线与消融构建、事后分析和报告撰写，由 meta-controller 管理并行研究智能体并在各阶段执行 rubric 验证。
正文 · 原文
Abstract: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.
| Comments: | 88 pages |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.18933 [cs.AI] |
| (or arXiv:2610.18933v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18933 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Robert Tjarko Lange [view email]
[v1]
Tue, 13 Oct 2026 11:28:03 UTC (30,709 KB)
来源：arXiv cs.CL · arxiv.org