OpenAI4S: Code as Action, Science as Sessions

• URL: http://arxiv.org/abs/2609.15096v1
• Date: Mon, 14 Sep 2026 06:16:59 GMT
• Title: OpenAI4S: Code as Action, Science as Sessions
• Abstract summary: We present OpenAI4S, an open-source scientific research agent built around the principle of emphCode as Action, Science as Sessions.<n>OpenAI4S combines a persistent computing runtime with research-session management orchestration is handled through structured tool calls.<n>We evaluate OpenAI4S on 36 research scenarios spanning retrosynthesis, molecular protein binder design, protein mutation, catalyst screening, and mineral spectroscopy.
• Score: 57.428071188574
• License: http://creativecommons.org/licenses/by/4.0/
• 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}.

Related papers

• MDArena: Evaluating Coding Agents on Realistic Molecular Dynamics Workflows [20.54127577222597]
  We introduce MDArena, a benchmark of 50 containerized tasks drawn from active biomolecular simulation projects.<n>We evaluate six model/harness configurations spanning Codex and OpenCode.<n>Among the evaluated configurations, Codex GPT-5.5 at extra-high reasoning effort performs best, reaching 24/50 Strict successes@1 (48%), followed by Codex GPT-5.5 Medium with 21/50, and OpenCode Gemini Flash 3.5 with 20/50.
  arXiv  Detail & Related papers  (2026-07-31T13:48:07Z)
• SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery [48.99744520105086]
  SciForge is a multimodal research-native AI workbench.<n>It reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services.
  arXiv  Detail & Related papers  (2026-07-17T15:13:03Z)
• Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery [51.70607714288616]
  Science Earth is a planet-scale scientific runtime in which any capability can connect to any other.<n>Its underlying EACN protocol lets capabilities discover one another, negotiate task ownership, and adjudicate across incompatible evidentiary standards.<n>Two runs validate this under structurally distinct conditions.
  arXiv  Detail & Related papers  (2026-05-31T16:05:41Z)
• NeuroClaw Technical Report [54.14941057366186]
  NeuroClaw is a domain-specialized multi-agent research assistant for neuroimaging research.<n>NeuroClaw operates directly on raw neuroimaging data across formats and modalities.<n>A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills.
  arXiv  Detail & Related papers  (2026-04-27T16:57:14Z)
• The Last Human-Written Paper: Agent-Native Research Artifacts [106.47848184955576]
  We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package.<n>Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste.
  arXiv  Detail & Related papers  (2026-04-27T16:23:09Z)
• BloClaw: An Omniscient, Multi-Modal Agentic Workspace for Next-Generation Scientific Discovery [7.409685482433176]
  BloClaw is a unified operating system designed for Artificial Intelligence for Science (AI4S)<n>We benchmark BloClaw across cheminformatics (RDKit), de novo 3D protein folding via ESM, molecular docking, and autonomous Retrieval-Plotmented Generation (RAG)<n>The open-source repository is available at https://github.com/qinheming/BloClaw.
  arXiv  Detail & Related papers  (2026-04-01T06:47:40Z)
• AI Co-Scientist for Ranking: Discovering Novel Search Ranking Models alongside LLM-based AI Agents with Cloud Computing Access [60.37646376282544]
  We present an AI Co-Scientist framework that automates the full search ranking research pipeline.<n>This is the first study in the ranking community to utilize an AI Co-Scientist framework for algorithmic research.
  arXiv  Detail & Related papers  (2026-03-23T09:29:08Z)
• Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis [23.28226188948918]
  ARIA is a spec-driven, human-in-the-loop framework for automated and interpretable data analysis.<n>ARIA integrates six layers, namely Command, Context, Code, Data, Orchestration, and AI Module.<n>ARIA establishes a new paradigm for transparent, collaborative, and reproducible scientific discovery.
  arXiv  Detail & Related papers  (2025-10-13T08:32:43Z)
• FROGENT: An End-to-End Full-process Drug Design Agent [19.025736969789566]
  Powerful AI tools for drug discovery reside in isolated web apps, desktop programs, and code libraries.<n>To address this issue, a Full-pROcess druG dEsign ageNT, named FROGENT, has been proposed.<n>FROGENT utilizes a Large Language Model and the Model Context Protocol to integrate multiple dynamic biochemical databases, tool libraries, and task-specific AI models.
  arXiv  Detail & Related papers  (2025-08-14T15:45:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.