Sakana AI 推出 The Agentic Scientist：用编码智能体自动做科研
Sakana AI 把 Codex、Claude Code 这类编码智能体包装成能自主做科研的系统，论文已被 ALIFE 2026 接收，代码和 arXiv 都放出来了。
Sakana AI 发布 The Agentic Scientist，把 Codex、Claude Code 等现成编码智能体包进一个脚手架，控制其输入、输出、评估与结果传递，让研究循环显式化。系统用实验前定义的评分标准测试假设，多个并行 worker 通过共享记忆交流成败，并对胜出程序做消融验证。团队用早期版本研究 Error Diffusion 这一替代反向传播的方法，论文被 ALIFE 2026 接收为口头报告。自主运行中，系统把 Doc-to-LoRA 多针检索准确率从 52% 提升到 98%，还设计出在未见任务上超过 CMA-ES 的学习型进化策略。
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
Blog: https://t.co/7aVDvZd6m2 GitHub: https://t.co/JCCBMvu2P1 arXiv: https://t.co/4bV76tAByj
Since 2024, we’ve used The AI Scientist as a way to test how far AI alone can take scientific research, from v1 to v2 to the paper published in Nature earlier this year. The Agentic Scientist is the next step in that line of work, built for the era of coding agents.
Coding agents such as Codex and Claude Code now carry out long software tasks on their own. Handing them a research problem, however, tends to produce a strong hyperparameter optimizer rather than a scientist: scores go up, but ideas stay narrow, and the reasons for the gain are rarely examined.
The Agentic Scientist makes the research loop explicit. It wraps off-the-shelf coding agents in a scaffold that controls what they see, what they write, how they are evaluated, and how results are handed to the next stage.
Parallel workers test hypotheses against rubrics defined before any experiment runs, share successes and failures through a common memory, and then ablate the winning program to generate evidence.
We used an early version of the system to study Error Diffusion, a biologically motivated alternative to backpropagation. Our researchers set the question and the rubric, chose directions at each stage, and verified the results, references, and claims before submission. The resulting paper was accepted as an oral presentation at ALIFE 2026. In autonomous runs, the system also raised Doc-to-LoRA retrieval accuracy from 52% to 98% on multi-needle tasks and designed a learned evolution strategy that improves over its CMA-ES reference on unseen tasks.
Alongside it we release AutoIllustrate, a pipeline for scientific figures that keeps an editable https://t.co/SHX9lrOr74 file as the source of truth, so every diagram can be corrected by hand.
Humans define the question and the standards of evidence; agents expand the experiments researchers can run. We call this Co-Discovery, and we are releasing both systems as open source for the community to build on.
