ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Hugging Face Daily Papers Papers
scientific-code agent-learning reinforcement-learning code-repair ai-research scientific-intelligence infrastructure

Summary

ScienceIDE introduces infrastructure for converting scientific code repositories into programmable environments for scientific agents, enabling task generation, execution, and verification, with trained models showing improvements in scientific code repair and general capabilities.

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE
Original Article
View Cached Full Text

Cached at: 09/17/26, 06:56 AM

Paper page - ScienceIDE: Turning World’s Scientific Codebase into Agent Learnable Environments

Source: https://huggingface.co/papers/2609.19134 Published on Sep 16

#1 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Scientificcoderepositoriesencodedecadesofhumanknowledgeinexecutablemodels,methods,andtools.Yetfragmentedtoolchains,implicitdomainconventions,andspecializedcorrectnesscriteriamakethisknowledgedifficulttoconvertintoreliablelearningexperience-achallengewecallthescientificexperiencebottleneck.WeintroduceScienceIDE,infrastructureforturningtheworld’sscientificcodeintoprogrammableenvironmentsforscientificagents.Guidedbyexpert-definedscientificcasesandacceptancecriteria,agentstransformrepositoriesintoexecutableenvironmentsthatsupporttaskgeneration,execution,andscientificverification.Theseenvironmentsprovideasharedfoundationforsupervisedfine-tuning,reinforcementlearning,andevaluation.Usingverifiedinteractiontrajectories,wetrainPhAI-IDE-72B,PhAI-IDE-9B,andPhAI-IDE-4B.Themodelfamilyshowsgainsinheld-outscientific-coderepairandacrossselectedgeneral-purposebenchmarksincode,reasoning,andknowledge,providingevidenceofpositivetransferfromscientificexperiencetobroadercapabilities.ScienceIDElaysthefoundationforanintegratedworkspaceforagentlearningandscientificpractice,makinghumanity’sscientificsoftwareasharedsubstratefordevelopingscientificintelligence.Code:https://github.com/aitofound/ScienceIDE

View arXiv pageView PDFProject pageGitHub5Add to collection

Get this paper in your agent:

hf papers read 2609\.19134

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.19134 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.19134 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.19134 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Rethinking Scientific Discovery in an Agentic Era

arXiv cs.CL

This paper presents SCION, an agentic scientific operating system that integrates AI tools for scientific discovery through a Research Execution Plan (REP) and hierarchical multi-agent execution. It demonstrates applications in materials analysis, molecule design, and protein screening, outperforming existing autonomous research-agent baselines.

Scientific computing in the age of agentic AI

OpenAI Blog

OpenAI shares a field report on using AI agents like Codex and Claude Code to assist in scientific computing projects, showing significant acceleration in software development and maintenance while shifting researchers' roles to verification and orchestration.

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

Papers with Code Trending

EvoScientist is an adaptive multi-agent framework for end-to-end scientific discovery that continuously improves through persistent memory modules, comprising three specialized agents for idea generation, experiment execution, and knowledge distillation. It outperforms 7 state-of-the-art systems in scientific idea generation and improves code execution success rates through multi-agent evolution.