Sebastian Pokutta

Artificial Intelligence, Optimization, and Machine Learning. Professor @TUBerlin, Vice President @ZuseInstitute, Chair @MATH+, Chair @MODAL

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. Schiekiera, L., Zimmer, M., Roux, C., Arnold, M., Pokutta, S., and Günther, F. (2026). LinearPFN: Amortized Variable Selection for Linear Models with Interactions. Preprint. [arXiv] mlprobabilitysparsity
  2. Pelleriti, N., Mundinger, K., Zimmer, M., and Pokutta, S. (2026). Zero: A Meta-Agent for Mathematical Research. Proceedings of the First NeurIPS Workshop on Meta Agents: Managing Agents That Manage Agents (Meta-Agents). agenticai4mathml
  3. Pelleriti, N., Kraus, N., May, A., and Pokutta, S. (2026). CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research. Proceedings of the Third NeurIPS Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD). agenticcryptanalysisllmml
  4. Pelleriti, N., Kraus, N., May, A., and Pokutta, S. (2026). CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research. Proceedings of the NeurIPS 2026 Workshop on Secure and Trustworthy Quantum Machine Learning (SaTQuML). agenticcryptanalysisllmml (Oral Presentation + Workshop)
  5. Djurdjevac Conrad, N., Pokutta, S., and Schuette, C. (2026). Measuring Model-Specific Alignment Drift in LLM-Based Opinion Dynamics. Proceedings of the Second NeurIPS Workshop on Large Language Models for Social Reasoning and Simulation (SocialAgent). haiillmmlmultiagentsocial
  6. Pelleriti, N., Mundinger, K., Zimmer, M., and Pokutta, S. (2026). Zero: A Meta-Agent for Mathematical Research. Proceedings of the Sixth NeurIPS Workshop on Mathematical Reasoning and AI (MATH-AI). agenticai4mathml
  7. Halbey, J., Roux, C., and Pokutta, S. (2026). Curvature-Dependent Lower Bounds for Frank-Wolfe. To Appear in Proceedings of NeurIPS. [arXiv] complexityfwlowerboundsopt
  8. Pokutta, S. (2026). Frank-Wolfe Beyond 1/t Convergence. To Appear in Proceedings of NeurIPS. [arXiv] complexityfwopt
  9. Petit-Tichanné, U., Pelleriti, N., Zimmer, M., and Pokutta, S. (2026). Learning the Coefficients of the Standard Volatility Forecaster. Proceedings of the NeurIPS 2026 Workshop on Generalization for Time Series in Tight Settings: Latency, Inference, Memory, PrIvacy and SusTainability (TS-LIMITS). financeml
  10. Wagner, M., Roux, C., Zimmer, M., and Pokutta, S. (2026). A Free Lunch in LLM Compression: Revisiting Retraining after Pruning. To Appear in Proceedings of NeurIPS. [arXiv] llmmlpruningsparsity
  11. Haase, J., Gonnermann-Müller, J., Hanel, P. H. P., Leins, N., Kosch, T., Mendling, J., and Pokutta, S. (2026). Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks. To Appear in Proceedings of NeurIPS. [arXiv] creativityhaiillmml
  12. 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). AlphaDiana: A System for Evaluating Reasoning Agents. Proceedings of the Sixth NeurIPS Workshop on Mathematical Reasoning and AI (MATH-AI). [visuals] agenticai4mathevaluationllmml
  13. 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). AlphaDiana: A System for Evaluating Reasoning Agents. Proceedings of the NeurIPS 2026 Workshop on Towards Test-Time Continual Learning Agents (TTCL). [visuals] agenticai4mathevaluationllmml
  14. Koshizuka, T., Blessing, D., Zimmer, M., Pokutta, S., and Richter, L. (2026). A Trust Region Approach for Learning Schrödinger Bridges. To Appear in Proceedings of NeurIPS. mloptprobability
  15. Leins, N., Pelleriti, N., Gonnermann-Müller, J., and Pokutta, S. (2026). When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Resources, and Task Difficulty. Proceedings of the NeurIPS 2026 Workshop on Resource-Aware Agentic AI (RAAAI). agenticevaluationllmml
  16. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? Proceedings of the NeurIPS 2026 Workshop on Self-Evolving Diversity-Driven Search for Robust AI Systems (EvoRobust). agenticai4mathllmml
  17. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). The Weight Distribution of the Third-Order Reed-Muller Code of Length 2048. Preprint. [arXiv] algebracombinatoricscompalginformationtheory
  18. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2026). Limits of Combinatorial Patchworking. Preprint. [arXiv] ai4mathalggeomcombinatoricscompalg
  19. Deza, A., Gerard, Y., Ma, Y., and Pokutta, S. (2026). Bounded-Support Additive Latin Transversals via Color-Counted Matching. Preprint. [arXiv] combinatoricsgraphs
  20. 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
  21. Kaibel, V., and Pokutta, S. (2026). A Counterexample to Ziegler’s Cross-Polytope Conjecture for Simplicial 0/1-Polytopes. Preprint. [arXiv] combinatoricsopt
  22. Pokutta, S. (2026). Symmetric Extension Complexity of the Spanning Tree Polytope. Preprint. [arXiv] extendedformulationipopt
  23. 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
  24. 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)
  25. 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). [visuals] agenticai4mathevaluationllmml
  26. 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). [visuals] agenticai4mathevaluationllmml
  27. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). Classification of Boolean Cubic Forms in Ten Variables. Preprint. [arXiv] algebracombinatoricscompalg
  28. 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
  29. 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
  30. 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] agenticai4mathllmml
  31. 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
  32. 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
  33. 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] [summary] mlxai (Spotlight + Conference Proceedings)
  34. 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
  35. 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). [PDF] [arXiv] compalgcomputational (Distinguished Student Author Award at ISSAC 2026)
  36. 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
  37. 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
  38. Haase, J., and Pokutta, S. (2026). The Hidden Cost of Tokenization: Why (most) Non-English Speakers Pay More for Less. Preprint. [arXiv] [summary] fairnessllmmlmultilingual
  39. Braun, G., Carderera, A., Combettes, C. W., Hassani, H., Karbasi, A., Mokhtari, A., and Pokutta, S. (2025). Conditional Gradient Methods. MOS-SIAM Series on Optimization. [PDF] [arXiv] mloptsurvey
  40. 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
  41. 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)

Recent Blog Posts

Select Outreach

(see archive for a complete list)

News

(see archive for a complete list)