The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
Robert Tjarko Lange, Luca Grillotti, Yutaro Yamada, Rujikorn Charakorn and David Ha (Sakana AI) present The Agentic Scientist, a distributed research pipeline in which a meta-controller runs parallel coding agents through every stage of a computational project and checks each stage against a rubric.
Ask this paper
Pipeline. Research is split into task drafting, idea generation, planning, sandboxed experiments, result aggregation, baseline and ablation construction, post-hoc analysis and report writing. Each stage is run by a coding agent that verifies its own output.
Meta-controller. One orchestration layer manages the parallel research agents and enforces rubric verification at every stage, so the same layer runs across domains with different execution environments, coding harnesses and metrics.
Peer-reviewed output. Used as a co-scientist tool on backpropagation-free error diffusion learning, a development version helped produce a paper that was accepted as an ALIFE 2026 main-conference talk after human verification and edits.
Autonomous runs. Run without a human, the system works on open ML problems including hypernetwork-based LLM adaptation, evolutionary optimization and RL fine-tuning, plus five more domains.
Ablations. Reliable autonomy depends on the cross-agent orchestration layer as well as on base model capability.
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.