ICML 2026 Workshop

AI as a Tool for Mathematics, Computer Science, and Machine Learning

Helping researchers integrate AI into core research workflows

📍 Seoul, South Korea 📅 July 10 or 11, 2026 Contact: ai4research-icml@googlegroups.com Submit: OpenReview

Why This Workshop

Modern AI systems can accelerate real research, but using them effectively remains nontrivial. This workshop will develop a community resource of workflows to drive progress at the AI–Math/CS/ML interface — especially in machine learning, optimization, statistics, algorithms, and adjacent areas.

While some researchers focus on how AI may be able to work on research independently, others are eager to share how AI is able to help humans in their research. However, it is often difficult to extract and reproduce the specific, frequently complex, workflows and “tricks” used by these researchers. As the degree of usefulness of generative AI depends greatly on the workflow, many scientists who currently only use AI for basic tasks, can substantially benefit from access to these methods. Our workshop aims to help researchers at ICML – especially in machine learning, optimization, statistics, algorithms, and adjacent areas – to more effectively integrate AI tools in their core research workflow. The workshop will cover:

AI-Assisted Workflows

Iterative verification loops, failure modes and how to detect them, prompting patterns that improve correctness, decomposition and self-critique, multi-agent strategies, and when to switch from informal to formal reasoning.

Tool-Augmented Reasoning

Integrating LLMs with computation (code, symbolic algebra, numerics), literature navigation, and proof assistants (e.g., Lean) to reduce hallucinations.

Research Acceleration

Using AI for derivations, counterexample search, and experiment design — with an emphasis on methods that transfer across subfields.

Contribute Your Work

We welcome submissions that highlight workflows using AI for machine learning, math, and computer science research more generally. Your contribution should illustrate—in an accessible way for a non-expert—how a simple workflow has proven to be useful in solving a cognitive research task (e.g., time-saving, energy-saving, result-strengthening, etc.).

The workflow should be reproducible by ML researchers within a few hours and with academic-level financial resources. Therefore, the workflow should either involve simple prompting-based strategies, or more sophisticated strategies where the submitters provide a package/agent/repository that can be readily integrated into a chat interface or an API call. All accepted submissions will be made publicly accessible, creating a shared repository of AI-assisted research workflows.

We also welcome submissions that illustrate interesting failure modes, to improve the community's understanding of the limitations of AI assistance.

We focus on the following tasks where AI can help, and challenges associated with AI-assisted research:

  • AI-assisted research problem formulation
  • AI-assisted experiment design for ML research
  • Solving mathematical research problems with AI assistance
  • Formalization of mathematical research, especially as it is relevant for machine learning
  • Verification of AI-generated proofs
  • Automation of iterative loops
  • Other tasks that are integral to an AI-assisted research workflow

The focus is on how researchers can become more productive, more rigorous, and do better research with the help of AI, and less on autonomous AI research, which is the focus of another exciting workshop: AI4Math.

In order to maintain focus, our workshop will not consider tasks that are not research-centered, such as simple writing, basic literature search (aka “deep research”), slide and poster creation, and pure software engineering (e.g., installing packages, version compatibility, etc.). There are already many resources available for such tasks.

What to include in your submission:

  • Explain the cognitive task that appeared in your research, for which AI has either significantly saved your time, or improved the results that you could obtain otherwise. Estimate the time-savings or performance improvements.
  • Describe the AI workflow you used in a way that is reproducible and usable by other researchers in a few hours.
    • This may include specific prompting techniques, code to call the API (once or repeatedly), a detailed description of how you set up the agentic frameworks, etc.
    • If your workflow relies on web-based prompting, share the exact prompt and ideally the exact transcripts of your conversation.
    • If your workflow relies on an API-based interaction and/or agentic research, provide a link to a repository with your code.
    • If applicable, discuss failure modes and what you learned from them.
  • Ensure that submissions are as close as possible to the working workflow itself. We aim to convert as many submissions as possible into workflows to test their performance. Make sure that the workflow is reproducible, including a README explaining how to install packages, and include any code that is not publicly available.
  • Explain how you verified the correctness of the results.

The contributions will be evaluated according to accessibility, reproducibility and correctness.

Submission Format

  • 4-page paper (excluding references and supplementary materials); detailed walkthroughs, screenshots, and conversation transcripts can be included in the appendix
  • Must follow ICML 2026 format
  • Indicate preferred presentation: computer demo or poster
  • Submissions via OpenReview

Policies

  • Non-archival: papers published at other venues are welcome
  • Double-blind review: submissions must be anonymized
  • Accepted papers will be presented as demos or posters; select papers may be invited for contributed talks
  • Review criteria: accessibility, reproducibility and correctness

Important Dates

  • Submission deadline: May 13, 2026
  • Notification of acceptance: May 31, 2026
  • Workshop date: July 10 or 11, 2026

All deadlines are Anywhere on Earth (AoE)

Photo of Sergei Gukov
Sergei Gukov
Caltech · American Institute of Mathematics

Sergei Gukov is the John D. MacArthur Professor of Theoretical Physics and Mathematics at Caltech, Director of the Merkin Center for Pure and Applied Mathematics, and Consulting Director of the American Institute of Mathematics. His research interests include mathematics and machine learning, quantum topology, gauge theory, and knot and 3-manifold invariants.

Photo of Remy Degenne
Remy Degenne
University of Lille · Inria

Remy Degenne is a tenured researcher in the Scool team at the Inria centre at the University of Lille. He works on sequential machine learning, especially bandit theory, and is interested in online and reinforcement learning, statistics, and optimization. He is also a maintainer of Mathlib for the Lean theorem prover.

Photo of Damek Davis
Damek Davis
University of Pennsylvania

Damek Davis is an Associate Professor in Wharton's Department of Statistics and Data Science. His research interests are optimization and machine learning, and he also works on AI for mathematics. He is currently an associate editor at Mathematical Programming and Foundations of Computational Mathematics.

Photo of Rachel Ward
Rachel Ward
UT Austin

Rachel Ward is the W. A. "Tex" Moncrief Distinguished Professor in Computational Engineering and Sciences - Data Science and professor of mathematics at UT Austin. She is recognized for contributions to sparse approximation, stochastic optimization, and numerical linear algebra. Her research lies broadly in the mathematics of data.

Photo of Mehtaab Sawhney
Mehtaab Sawhney
Columbia University / OpenAI

Mehtaab Sawhney is a Clay Research Fellow and a tenure-track assistant professor at Columbia University. His research interests are broadly within combinatorics, probability, analytic number theory, and theoretical computer science.

Full-Day Program

All times are local time in Seoul, South Korea (KST (UTC+9))

08:50–09:00
Introduction to the workshop
09:00–09:40
Talk: Sergei Gukov
Caltech · American Institute of Mathematics
09:40–10:20
Talk: Remy Degenne
University of Lille · Inria
10:20–10:35
Coffee break
10:35–11:15
Talk: Damek Davis
University of Pennsylvania
11:15–12:00
Demo and poster session of accepted submissions
12:00–13:00
Lunch
13:00–13:40
Talk: Rachel Ward
UT Austin
13:40–14:20
Talk: TBA
14:20–15:00
Demo and poster session of accepted submissions
15:00–15:15
Coffee break
15:15–15:55
Talk: Mehtaab Sawhney
Columbia University · OpenAI
16:00–17:00
Structured debate and panel

Structured Discussion

Four of the speakers will debate in teams of two (Affirmative vs. Negative) on the motion:

"Within five years, researchers at ICML today will consider AI-generated analyses, results, and written conclusions as reliable as those from leading theoretical researchers."

The debate follows a structured format with strict timing:

  • Opening speeches of 4 minutes each, presenting the main arguments
  • Crossfire of 2 minutes with alternating questions (10 sec) and answers (20 sec)
  • Rebuttal and new arguments with 3 minutes each
  • Second crossfire round of 2 minutes
  • Another round of rebuttal with 3 minutes each
  • Closing speech summarizing the debate, 3 minutes each

After the debate, questions from the audience will follow, moderated by the organizers.

Logistics

Location

COEX Convention & Exhibition Center
Seoul, South Korea

Part of ICML 2026 (July 6–11, 2026)

Workshop Dates

July 10 or 11, 2026
(ICML 2026 workshop days)

Full-day, in-person

Registration

Workshop attendance requires ICML 2026 registration.

A workshop-only registration is sufficient. Please register through the main conference website.

Workshop Committee

Photo of Mikhail Belkin
Mikhail Belkin
UC San Diego

HDSI Endowed Chair Professor in Artificial Intelligence at UC San Diego. His research spans artificial intelligence, machine learning, and high-dimensional statistics.

Photo of Sébastien Bubeck
Sébastien Bubeck
OpenAI

Member of Technical Staff at OpenAI. His work includes large language models, convex optimization, online algorithms, and adversarial robustness.

Photo of Edgar Dobriban
Edgar Dobriban
University of Pennsylvania

Associate Professor of Statistics and Computer & Information Science at Penn. His research sits at the interface of statistics, machine learning, and AI.

Photo of Dmitriy Drusvyatskiy
Dmitriy Drusvyatskiy
UC San Diego

Professor at the Halicioglu Data Science Institute at UC San Diego. His research interests are in optimization, high-dimensional statistics, machine learning, and AI.

Photo of Ravi Vakil
Ravi Vakil
Stanford University

Robert Grimmett Professor of Mathematics at Stanford University and President of the American Mathematical Society. He works in algebraic geometry.

Photo of Fanny Yang
Fanny Yang
ETH Zürich

Assistant Professor of Computer Science at ETH Zurich. She works on high-dimensional and robust machine learning.

Get Involved

Call for volunteers: our workshop aims to serve the needs of the community, and be community-driven. If you are interested in volunteering, please contact us. Sign up to help review contributions, build a platform to share workflows and make them easily accessible and searchable, or support the workshop in other ways.

Interested in volunteering? Sign up here.

Photo of Federico Di Gennaro
Federico Di Gennaro
ETH Zürich

Federico Di Gennaro is a PhD student at ETH Zürich, advised by Prof. Fanny Yang. His research interests include statistical learning and trustworthy ML.

Photo of Sunay Joshi
Sunay Joshi
University of Pennsylvania

Sunay Joshi is a PhD student at the University of Pennsylvania, advised by Prof. Edgar Dobriban and Prof. Hamed Hassani. His research interests include conformal prediction and uncertainty quantification for AI.

Photo of Qingsong Wang
Qingsong Wang
UC San Diego

Qingsong Wang is a postdoctoral researcher at UC San Diego, working with Prof. Mikhail Belkin and Prof. Yusu Wang. His research interests include diffusion and flow-matching generative models, data geometry, and representation learning.

Photo of Tao Wang
Tao Wang
University of Pennsylvania

Tao Wang is a PhD student in Statistics and Data Science at the University of Pennsylvania, advised by Prof. Edgar Dobriban. His research interests include uncertainty quantification, optimal transport, and LLM post-training.