Research Lab

My group works on Artificial Intelligence, Optimization, and Machine Learning; from foundational algorithms to real-world systems. We develop new optimization and learning methods with a focus on efficiency and sustainability, combine learning with decision-making, and build agentic AI systems for complex tasks. A particular focus is on AI4Science and AI4Math, where we use AI to drive mathematical discovery and scientific insight. Recent examples include global forest monitoring from satellite data, entanglement certification via optimization, new constructions in extremal combinatorics, AI-assisted mathematical proofs, and AI for creativity and education. group homepage more about research and projects

TL;DR. We use computers to learn from data and make better decisions.

ETC. Hashed Commitments AI News

Prospective Students. If you are interested in working in our group or writing your MS/BS thesis please check our openings.

Select Recent Papers

(see publications for a complete list)

1. Zimmer, M., Pelleriti, N., Roux, C., and Pokutta, S. (2026). The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning. Proceedings of the 3rd ICML Workshop on AI for Mathematics (AI4Math). [PDF] [arXiv] [code] agenticai4mathml
2. Zimmer, M., Pelleriti, N., Roux, C., and Pokutta, S. (2026). The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning. Proceedings of the ICML 2026 Workshop on AI as a Tool for Mathematics, Computer Science, and Machine Learning (AI4Research). [PDF] [arXiv] [summary] [code] agenticai4mathml (Oral Presentation + Workshop)
3. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks. Proceedings of the ICML 2026 Workshop on AI as a Tool for Mathematics, Computer Science, and Machine Learning (AI4Research). agenticevaluationllmml
4. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks. Proceedings of the 3rd ICML Workshop on AI for Mathematics (AI4Math). agenticai4mathevaluationllmml
5. Haase, J., Gonnermann-Müller, J., Yim, S. H., Leins, N., Mendling, J., and Pokutta, S. (2026). Simulating Eating Disorder Patients with LLMs: Evaluating Psychological Persona Stability in Multi-Turn Conversations. Preprint. [arXiv] haiillmmlmultiagentsocial
6. Pokutta, S. (2026). Symmetric Extension Complexity of the Spanning Tree Polytope. Preprint. [arXiv] extendedformulationipopt
7. Muhtar, D., Song, X., Pokutta, S., Zimmer, M., Pelleriti, N., Hofmann, T., and Liu, S. (2026). When Does Sparsity Mitigate the Curse of Depth in LLMs. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [code] llmmlsparsity
8. Haase, J., and Pokutta, S. (2026). Structured Creativity Methods for Multi-Agent LLMs: Brainwriting Outperforms Disney and Double Diamond. Proceedings of ICML 2026 Workshop on Human-AI Co-Creativity (GenAICreativity). creativityllmmlmulti-agent
9. Haase, J., and Pokutta, S. (2026). The Missing Drive: Functional Analogs of Intrinsic Motivation in Large Language Models for Creative Tasks. Proceedings of ICML 2026 Workshop on Human-AI Co-Creativity (GenAICreativity). creativityllmml
10. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? Preprint. [arXiv] agenticllmmlneuro-compute
11. Halbey, J., Deza, D., Zimmer, M., Roux, C., Stellato, B., and Pokutta, S. (2026). Lower Bounds for Frank-Wolfe on Strongly Convex Sets. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [summary] complexityfwlowerboundsopt
12. Schiekiera, L., Zimmer, M., Roux, C., Pokutta, S., and Günther, F. (2026). From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [summary] cognitivellmmlxai
13. Turan, B., Asadulla, S., Steinmann, D., Kersting, K., Stammer, W., and Pokutta, S. (2026). Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] mlxai (Spotlight + Conference Proceedings)
14. Pokutta, S. (2026). Frank-Wolfe Beyond 1/t Convergence. Preprint. [arXiv] complexityfwopt
15. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). Faster Algorithms for Structured Matrix Multiplication via Flip Graph Search. Proceedings of the International Symposium on Symbolic and Algebraic Computation (ISSAC). [arXiv] compalgcomputational
16. Zimmer, M., Pelleriti, N., Roux, C., and Pokutta, S. (2026). The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning. Preprint. [arXiv] [summary] [code] agenticai4mathml
17. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2026). Patchworked Curves of Degree Seven. Preprint. [arXiv] ai4mathalggeomcombinatoricscompalg
18. Pelleriti, N., Spiegel, C., Liu, S., Martínez-Rubio, D., Zimmer, M., and Pokutta, S. (2026). Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers. To Appear in Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] ai4mathcompalgml
19. Haase, J., and Pokutta, S. (2026). The Hidden Cost of Tokenization: Why (most) Non-English Speakers Pay More for Less. Preprint. [arXiv] [summary] fairnessllmmlmultilingual
20. Braun, G., Carderera, A., Combettes, C. W., Hassani, H., Karbasi, A., Mokthari, A., and Pokutta, S. (2025). Conditional Gradient Methods. MOS-SIAM Series on Optimization. [PDF] [arXiv] mloptsurvey
21. Abbas, A., Ambainis, A., Augustino, B., Bärtschi, A., Buhrman, H., Coffrin, C., Cortiana, G., Dunjko, V., Egger, D. J., Elmegreen, B. G., Franco, N., Fratini, F., Fuller, B., Gacon, J., Gonciulea, C., Gribling, S., Gupta, S., Hadfield, S., Heese, R., … Zoufal, C. (2024). Quantum Optimization: Potential, Challenges, and the Path Forward. Nature Reviews Physics. [PDF] [arXiv] optphysicsquantumsurvey
22. Pokutta, S. (2024). The Frank-Wolfe algorithm: a short introduction. Jahresbericht Der Deutschen Mathematiker-Vereinigung, 126, 3–35. [PDF] [arXiv] mlopt

Select Recent Talks and Teaching

(see archive for a complete list)

• 06/2026: (technical) “How Machines Explore, Conjecture, and Discover Mathematics”. Talk at Mathematics Colloquium / Structure, Methods, and Theory Center (Jena, Germany). [slides]
• 06/2026: (general) “The Cargo Cult Meets Large Language Models: Demystifying AI Sentiments?”. Talk at Lange Nacht der Wissenschaften (Berlin, Germany).
• 06/2026: (technical) “Efficient Quadratic Corrections for Frank-Wolfe Algorithms”. Talk at SIAM Conference on Optimization (OP26) (Edinburgh, Scotland). [slides]
• 05/2026: (technical) “When Algorithms Learn: Discrete Optimization Meets Machine Learning”. Talk at TRR 154 Abschlusstagung — Mathematical Modelling, Simulation and Optimization (Gas Networks) (Nürnberg, Germany). [slides]
• 05/2026: (technical) “When Algorithms Learn: Discrete Optimization Meets Machine Learning”. Plenary at ISCO 2026 - 9th International Symposium on Combinatorial Optimization (Kuşadası, Turkey). [slides]
• SS/2026: Discrete Optimization and Machine Learning (seminar)

Recent Blog Posts

• 06/2026: The Zeroth World: A Seven-Year Update
• 05/2026: The Hidden Cost of Tokenization
• 04/2026: Not every discovery needs an LLM
• 04/2026: An uncommon approach to lower bounds for Frank-Wolfe on strongly convex sets
• 03/2026: The Agentic Researcher

Select Outreach

(see archive for a complete list)

• 05/2026: Der Traum der Gurke – Ein literarisches KI-Experiment. Weizenbaum-Institut. (Panel Discussion (German))
• 04/2026: Mehr als die Summe der Teile — Multi-Agenten-Systeme: Wie KI-Systeme gemeinsam Probleme lösen. c't 10/2026, pp. 120–125 (Heise). (Magazine feature (German))
• 11/2024: El aprendizaje automático ayuda a atacar problemas matemáticos clásicos (Machine learning helps attack classical mathematical problems). El Pais: Café y teoremas. (Newspaper (Spanish))
• 11/2024: Zukunftsforum KI. IHK Berlin. (Panel Discussion (German))
• 10/2021: Improve the World with Maths?. Humboldt Forum: Discourse, Science and Humanities. (Talk + Discussion (German))

News

(see archive for a complete list)

• 05/2026: Together with G. K. Tjusila, A. Hoen, N.-C. Kempke, G. Mexi, T. Berthold, A. Gleixner, and T. Koch, we won the Land-Doing MIP Computational Competition 2026.
• 04/2026: Six papers papers accepted this month at ICML (including one spotlight!), ISSAC, and IJCAI. Congratulations everyone!
• 01/2026: Kartikey Sharma accepted an Assistant Professor position in the Mechanical Engineering Department at IIT Delhi. Congratulations!
• 10/2025: Our book on Conditional Gradients and Frank-Wolfe methods has been published in the MOS-SIAM Series on Optimization.
• Fall 2025: Sai Ganesh Nagarajan started a Tenure Track Assistant Professor Position at the Department of Mathematics and Computer Science (IMADA), Southern Denmark University, Odense, Denmark. Congratulations!