# ScienceIDE — scientific codebases become training grounds for agents

> Real scientific code repositories, turned into environments where agents are graded on numerical correctness.

- Org: AItonomy Foundation
- Date: 2026-09-16
- Category: paper, repo, model
- Source: https://arxiv.org/abs/2609.19134
- Canonical page: https://ai-tldr.dev/releases/aitonomy-scienceide/

## In short

ScienceIDE turns real scientific code repositories into executable environments where AI agents are trained and graded on numerical correctness. The AItonomy Foundation also released three open PhAI-IDE models at 4B, 9B and 72B.

## What it is

ScienceIDE converts scientific code repositories — astrophysics, ocean modelling, neuroscience simulation — into programmable environments for AI agents. The AItonomy Foundation published 15 of its 64 environments plus the RL code and 30 of 85 ScienceIDE-Hard tasks, and released three open PhAI-IDE models at 4B, 9B and 72B trained on verified trajectories.

## How it works

Agents repair injected defects in real scientific simulations by editing source code, and the reward comes from numerical correctness checks rather than matching a reference diff. Expert-defined scientific cases and acceptance criteria guide how each repository becomes a task, and the resulting verified trajectories feed supervised fine-tuning, reinforcement learning and evaluation from one shared foundation.

## Why it matters

Decades of domain knowledge sit in scientific software that generic code benchmarks never touch, which the authors call the scientific experience bottleneck. The project reports the PhAI-IDE family also improving on general tests — 6.99 points on CodeXGLUE defect detection and 36.00 points on BBH Word Sorting — which it reads as evidence that scientific experience transfers to broader coding and reasoning.

## Who it's for

scientific-agent and RL researchers

## Try it

https://huggingface.co/collections/AItonomy/scienceide-model-series

## Links

- [Paper](https://arxiv.org/abs/2609.19134)
- [Code](https://github.com/aitofound/ScienceIDE)
- [Models](https://huggingface.co/collections/AItonomy/scienceide-model-series)
- [Paper Page](https://huggingface.co/papers/2609.19134)
- [Project Page](https://aitonomy.org/projects/scienceide)