---
title: "AIDE: AI-Driven Exploration in the Space of Code (2025)"
description: "This paper presents AIDE, an LLM-based agent from Weco AI that treats ML engineering as the… 13 references, cited by 46 papers here."
authors: ["Zhengyao Jiang", "Dominik Schmidt", "Dhruv Srikanth", "Dixing Xu", "Ian Kaplan", "Deniss Jacenko", "Yuxiang Wu"]
year: 2025
venue: "arXiv:2502.13138"
source: "https://arxiv.org/abs/2502.13138"
doi: "10.48550/arxiv.2502.13138"
arxiv: "2502.13138"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/jiang-2025-aide-ai-driven-exploration/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/jiang-2025-aide-ai-driven-exploration/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/) / AIDE: AI-Driven Exploration in the Space of Code

# AIDE: AI-Driven Exploration in the Space of Code

**Authors:** Zhengyao Jiang, Dominik Schmidt, Dhruv Srikanth, Dixing Xu, Ian Kaplan, Deniss Jacenko and [Yuxiang Wu](https://md.research.elamur.ai/free/en/authors/yuxiang-wu/) · **Year:** 2025 · **Venue:** arXiv:2502.13138 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2502.13138) · [PDF](https://arxiv.org/pdf/2502.13138) · [DOI 10.48550/arxiv.2502.13138](https://doi.org/10.48550/arxiv.2502.13138) · [arXiv 2502.13138](https://arxiv.org/abs/2502.13138) · [OpenAlex](https://openalex.org/W4407760093)

**Citations:** 4 citations (OpenAlex, 2026-10-14) · [46](https://md.research.elamur.ai/free/en/papers/jiang-2025-aide-ai-driven-exploration/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Developing strong machine learning models depends heavily on repetitive trial-and-error. Classic automation methods such as AutoML, NAS and hyperparameter search also require a hand-designed configuration space. This paper presents AIDE, an LLM-based agent from Weco AI that treats ML engineering as the optimization of code itself. ReAct-style agents keep appending to an ever-growing interaction history. AIDE instead stores every candidate script as a node in a solution tree and scores each one with a stateless evaluator, such as a validation metric. A fixed heuristic policy then decides whether to write a fresh draft, repair a failing script, or apply one atomic change to the current best solution. A summarization step condenses earlier attempts, and a small data preview is added to prompts, so context stays compact. AIDE was tested on the authors' Kaggle tabular tasks, OpenAI's MLE-Bench and METR's RE-Bench. It reached state-of-the-art results and sometimes outperformed human experts under time limits. This shows that structured search over code can turn extra compute into better ML solutions. The implementation is open source.

## Key points
- The core loop has four components: a search policy π (draft / debug / improve), a coding operator f, a summarization operator Σ(T), and an evaluator h that scores each script independently. Code is available at github.com/WecoAI/aideml.
- On MLE-Bench, AIDE earned roughly twice as many medals as a later competing agent when both used GPT-4o, and the gap grew further with o1-preview.
- On the MLE-Bench Lite subset with o1-preview, adding AIDE improved results as follows (all p \< 0.01):
  - valid submissions rose from 63.6% to 92.4%;
  - above-median-human scores rose from 13.6% to 59.1%;
  - gold medals rose from 6.1% to 21.2%;
  - any medal rose from 7.6% to 36.4%.
- On RE-Bench, METR compared AIDE + o1-preview with top human researchers across 7 AI R&D tasks:
  - AIDE scored higher within a six-hour budget.
  - In Optimize a Kernel, it found a custom Triton solution faster than any of nine experts working up to 64 hours.
- Limitations: the greedy policy can get stuck in local optima, so humans eventually caught up. AIDE also struggled with large codebases and multi-step changes, for example repeating local patches in Agent for Rust CodeContests.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,888 works

## Cite

Cite as: Zhengyao Jiang, Dominik Schmidt, Dhruv Srikanth, Dixing Xu, Ian Kaplan, Deniss Jacenko and Yuxiang Wu. 2025. AIDE: AI-Driven Exploration in the Space of Code. arXiv:2502.13138.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{jiang2025aide,
  title = {{AIDE: AI-Driven Exploration in the Space of Code}},
  author = {Zhengyao Jiang, Dominik Schmidt, Dhruv Srikanth, Dixing Xu, Ian Kaplan, Deniss Jacenko and Yuxiang Wu},
  year = {2025},
  doi = {10.48550/arxiv.2502.13138},
  eprint = {2502.13138},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2502.13138}
}
```

- [← previous Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching](https://md.research.elamur.ai/free/en/papers/aytes-2025-sketch-thought-efficient-llm-reasoning/)
- [next → AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset](https://md.research.elamur.ai/free/en/papers/moshkov-2025-aimo-2-winning-solution-building/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

13 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. Claude 3.5 sonnet model card addendum. Technical report, Anthropic, 2024. URL [https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/](https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/) Model_Card_Claude_3_Addendum.pdf. [↗](https://www-cdn.anthropic.com/fed9cc193a14b84131812372d8d5857f8f304c52/)
2. J. S. Chan, N. Chowdhury, O. Jaffe, J. Aung, D. Sherburn, E. Mays, G. Starace, K. Liu, L. Maksin, T. Patwardhan, L. Weng, and A. M adry. [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://md.research.elamur.ai/free/en/papers/chan-2024-mle-bench-evaluating-machine/). arXiv preprint arXiv:2410.07095, 2024.
3. T. Elsken, J. H. Metzen, and F. Hutter. Neural architecture search: A survey. Journal of Machine Learning Research, 20(55):1–21, 2019. [find](https://scholar.google.com/scholar?q=T%2E+Elsken%2C+J%2E+H%2E+Metzen%2C+and+F%2E+Hutter%2E+Neural+architecture+search%3A+A+survey%2E+Journal+of+Machine+Learning+Research%2C+20%2855%29%3A1%E2%80%9321%2C+2019%2E)
4. S. Falkner, A. Klein, and F. Hutter. BOHB: Robust and Efficient Hyperparameter Optimization at Scale. In Proc. of ICML, volume 35, 2018. [find](https://scholar.google.com/scholar?q=S%2E+Falkner%2C+A%2E+Klein%2C+and+F%2E+Hutter%2E+BOHB%3A+Robust+and+Efficient+Hyperparameter+Optimization+at+Scale%2E+In+Proc%2E+of+ICML%2C+volume+35%2C+2018%2E)
5. M. Feurer, A. Klein, K. Eggensperger, J. T. Springenberg, M. Blum, and F. Hutter. Efficient and Robust Automated Machine Learning. In Proc. of NeurIPS, volume 28, 2015. [find](https://scholar.google.com/scholar?q=M%2E+Feurer%2C+A%2E+Klein%2C+K%2E+Eggensperger%2C+J%2E+T%2E+Springenberg%2C+M%2E+Blum%2C+and+F%2E+Hutter%2E+Efficient+and+Robust+Automated+Machine+Learning%2E+In+Proc%2E+of+NeurIPS%2C+volume+28%2C+2015%2E)
6. M. Feurer, K. Eggensperger, E. Bergman, F. Pfisterer, B. Bischl, and F. Hutter. Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning. arXiv preprint arXiv:2007.04074, 2020. — [arXiv:2007.04074](https://arxiv.org/abs/2007.04074) [find](https://scholar.google.com/scholar?q=M%2E+Feurer%2C+K%2E+Eggensperger%2C+E%2E+Bergman%2C+F%2E+Pfisterer%2C+B%2E+Bischl%2C+and+F%2E+Hutter%2E+Auto%2DSklearn+2%2E0%3A+Hands%2Dfree+AutoML+via+Meta%2DLearning%2E+arXiv+preprint+arXiv%3A2007%2E04074%2C+2020%2E+%E2%80%94+%5BarXiv%3A2007%2E04074%5D%28https)
7. Google. [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-team-2024-gemini-1-5-unlocking-multimodal/). arXiv preprint arXiv:2403.05530, 2024.
8. Qian Huang, Jian Vora, Percy Liang, and Jure Leskovec. [Mlagentbench: Evaluating language agents on machine learning experimentation](https://md.research.elamur.ai/free/en/papers/huang-2023-mlagentbench-evaluating-language-agents/). In Forty-first International Conference on Machine Learning, 2024.
9. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. [Livecodebench: Holistic and contamination free evaluation of large language models for code](https://md.research.elamur.ai/free/en/papers/jain-2024-livecodebench-holistic-contamination-free-evaluation/). In The Thirteenth International Conference on Learning Representations, 20…
10. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. [SWE-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) In The Twelfth International Conference on Learning Representations, 2024. URL [https://openreview.net/forum?id=VTF8yNQM66](https://openreview.net/forum?id=VTF8yNQM66). [↗](https://openreview.net/forum?id=VTF8yNQM66)
11. H. Jin, Q. Song, and X. Hu. Auto-Keras: An Efficient Neural Architecture Search System. In Proc. of ACM SIGKDD (KDD), 2019. [find](https://scholar.google.com/scholar?q=H%2E+Jin%2C+Q%2E+Song%2C+and+X%2E+Hu%2E+Auto%2DKeras%3A+An+Efficient+Neural+Architecture+Search+System%2E+In+Proc%2E+of+ACM+SIGKDD+%28KDD%29%2C+2019%2E)
12. H. Jin, F. Chollet, Q. Song, and X. Hu. AutoKeras: An AutoML Library for Deep Learning. Journal of Machine Learning Research, 24(6):1–7, 2023. [find](https://scholar.google.com/scholar?q=H%2E+Jin%2C+F%2E+Chollet%2C+Q%2E+Song%2C+and+X%2E+Hu%2E+AutoKeras%3A+An+AutoML+Library+for+Deep+Learning%2E+Journal+of+Machine+Learning+Research%2C+24%286%29%3A1%E2%80%937%2C+2023%2E)
13. Leslie Pack Kaelbling, Michael L Littman, and Anthony R Cassandra. Planning and acting in partially observable stochastic domains. Artificial Intelligence, 101(1-2):99–134, 1998. E. LeDell and S. Poirier. H2O AutoML: Scalable Automatic Machine Learning. In Proc. of the AutoML Conference, pages 1–8,… — [Competition-Level Code Generation with AlphaCode](https://md.research.elamur.ai/free/en/papers/li-2022-competition-level-code-generation-alphacode/)

*Updated 3 November 2026*