Skip to content

OpenAl4S: Code as Action, Science as Sessions

Sep 2026 · 0 citations · 22 references
Computer Science

TL;DR

The results suggest that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows, and recommend that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows.

Abstract

AI co-scientists could accelerate computational research, but over a long-running study the workflow also has to stay inspectable, resumable and reproducible, which requires persistent computational state and provenance. Here we present OpenAI4S, an open-source scientific research agent built around the principle of \emph{Code as Action, Science as Sessions}. OpenAI4S combines a persistent computing runtime with research-session management: orchestration is handled through structured tool calls, while scientific actions are represented as complete code cells executed in persistent Python and R kernels. An append-only Action Ledger, per-cell execution records, versioned artifacts, environment records, and workspace checkpoints preserve how results were produced and support session recovery, branching, and extension. Configurable sandboxing, permission controls, and code and trajectory screening provide complementary safeguards. We evaluate OpenAI4S on 36 research scenarios spanning retrosynthesis, molecular dynamics, protein binder design, protein mutation, catalyst screening, and mineral spectroscopy, measuring scientific task accuracy, workflow completeness, and reproducibility of the resulting repositories. OpenAI4S achieves an overall score of 7.83, compared with 5.7--6.4 for a general-purpose coding harness evaluated with three frontier models, with the largest gains on long-horizon and computation-intensive workflows. These results suggest that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows. Environment specification and full rerunnability remain weak for every evaluated system, ours included, so reproducibility is still an open problem for scientific agents. The system is available under the MIT license at \href{https://github.com/PKU-YuanGroup/OpenAI4S}{github.com/PKU-YuanGroup/OpenAI4S}.

View source

Similar papers

Open access 2026

Bohrium + SciMaster: Building the infrastructure and ecosystem for agentic science at scale

AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning, tool use, and verification. Scaling such agentic science remains difficult because workflows are hard to observe and reproduce, many scientific tools and laboratory systems are not agent-ready, and execution trac...

Lin-Feng Zhang, Si-Heng Chen, Yu-Zhu Cai et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Bioinfoysis Technical Report

A multi-agent harness that represents each request as a persistent, artifact-grounded analysis run, and demonstrates that reliable bioinformatics automation depends not only on model capability, but also on the harness that governs planning, execution, memory, and evidence flow.

Qi Shao, Xin Zhang, Zhou-Yang Yuan et al. · 0 citations
Review Open access Sep 2026

Designing reproducible large-language-model-assisted scientific analyses

Summary Large language models (LLMs) increasingly write code, analyze data, and orchestrate scientific workflows. This can create reproducibility challenges because LLMs blur the boundary between how an analysis is built and what it depends on at run time. Guidelines for LLM-assisted science begin with a critical choic...

C. Dunn, Darrin T. Schultz, J. Musser · 1 citation
#artificial intelligence Preprint Oct 2026

Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows

Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited. Existing evaluations often emphasize textual responses or isolated code generation rather than the validity of complete engineering arti...

Jorge García-Carrasco, Javier Sanchis, A. Reina-Reina et al. · 0 citations
Review Open access Sep 2026

From Prompt to Provenance: BloClaw, a Capability-Gated AI4S Workstation for Auditable Computational Biology

This manuscript reports the system design, verified capability boundary, deterministic software artifacts, and a reproducible evaluation protocol for BloClaw, an AI4S workstation built around a simple principle: a scientific agent should know what it can do, show how it did it, and state what remains unvalidated.

Yao Qin, Jin-Hua Pang, Xiao-Ming Zhang · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.