Nico Pelleriti

Nico Pelleriti

Contact

office
Room 3024 at ZIB
e-mail
homepage
pelleriti.org

Curriculum vitae

since 2025
Researcher at TUB
since 2024
Member of BMS
since 2023
Research Assistant at ZIB
Aug 2024
B.Sc. in Mathematics at TUB
Sep 2025
M.Sc. in Mathematics at TUB

Publications and preprints

Preprints and reports

  1. Leins, N., Pelleriti, N., Gonnermann-Müller, J., and Pokutta, S. (2026). When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty. [arXiv]
    [BibTeX]
    @misc{2026_LeinsPelleritiGonnermannmuellerPokutta_Llmorchestration_2608-00685,
      archiveprefix = {arXiv},
      eprint = {2608.00685},
      arxiv = {arXiv:2608.00685},
      primaryclass = {cs.AI},
      author = {Leins, Nicolas and Pelleriti, Nico and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Cost, and Task Difficulty},
      date = {2026-08-01}
    }
  2. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? [arXiv]
    [BibTeX]
    @misc{2026_PelleritiEtAl_Evotrace_2605-20086,
      archiveprefix = {arXiv},
      eprint = {2605.20086},
      arxiv = {arXiv:2605.20086},
      primaryclass = {cs.NE},
      author = {Pelleriti, Nico and Nelaturu, Sree Harsha and Zhou, Zhanke and Li, Zongze and Zimmer, Max and Han, Bo and Pokutta, Sebastian},
      title = {What Do Evolutionary Coding Agents Evolve?},
      date = {2026-05-19}
    }
  3. Pelleriti, N., Shiran, M., Martínez-Rubio, D., Zimmer, M., and Pokutta, S. (2026). Optimal Gradient-Norm Minimization in Non-Euclidean Hölder-Smooth Convex Optimization. [arXiv]
    [BibTeX]
    @misc{2026_PelleritiEtAl_GradientNormNonEuclidean_2609-01122,
      archiveprefix = {arXiv},
      eprint = {2609.01122},
      arxiv = {arXiv:2609.01122},
      primaryclass = {math.OC},
      author = {Pelleriti, Nico and Shiran, Maryam and Martínez-Rubio, David and Zimmer, Max and Pokutta, Sebastian},
      title = {Optimal Gradient-Norm Minimization in Non-Euclidean Hölder-Smooth Convex Optimization},
      date = {2026-09-01}
    }
  4. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Xie, Y., Pelleriti, N., Liu, S., Lu, M., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks. [arXiv]
    [BibTeX]
    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675,
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Lu, Menghan and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks},
      date = {2026-10-14}
    }
  5. 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. [arXiv]
    [BibTeX]
    @misc{2026_ZimmerPelleritiRouxPokutta_Airesearchframework_2603-15914,
      archiveprefix = {arXiv},
      eprint = {2603.15914},
      arxiv = {arXiv:2603.15914},
      primaryclass = {cs.LG},
      author = {Zimmer, Max and Pelleriti, Nico and Roux, Christophe and Pokutta, Sebastian},
      title = {The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning},
      date = {2026-03-16}
    }

Conference contributions

  1. 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, 306. Associated with ICML 2026. [arXiv]
    [BibTeX]
    @inproceedings{2026_DilxatEtAl_Sparsitydepthllms_2603-15389,
      year = {2026},
      booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {306},
      month = jul,
      archiveprefix = {arXiv},
      eprint = {2603.15389},
      arxiv = {arXiv:2603.15389},
      primaryclass = {cs.CL},
      author = {Muhtar, Dilxat and Song, Xinyuan and Pokutta, Sebastian and Zimmer, Max and Pelleriti, Nico and Hofmann, Thomas and Liu, Shiwei},
      title = {When Does Sparsity Mitigate the Curse of Depth in LLMs}
    }
  2. 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. International Conference on Learning Representations 2026. Associated with ICLR 2026. [URL] [arXiv]
    [BibTeX]
    @inproceedings{2025_PelleritiEtAl_Neuralsos_2510-13444,
      year = {2026},
      booktitle = {International Conference on Learning Representations 2026},
      publisher = {ICLR (OpenReview)},
      url = {https://proceedings.iclr.cc/paper_files/paper/2026/hash/1cfb3b066461f1c542be5242a622ce4b-Abstract-Conference.html},
      archiveprefix = {arXiv},
      eprint = {2510.13444},
      arxiv = {arXiv:2510.13444},
      primaryclass = {cs.LG},
      author = {Pelleriti, Nico and Spiegel, Christoph and Liu, Shiwei and Martínez-Rubio, David and Zimmer, Max and Pokutta, Sebastian},
      title = {Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers}
    }
  3. 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. Accepted at NeurIPS 2026 Workshop on Resource-Aware Agentic AI. [arXiv]
    [BibTeX]
    @misc{2026_LeinsPelleritiGonnermannmuellerPokutta_Llmorchestration_2608-00685:1,
      howpublished = {Accepted at NeurIPS 2026 Workshop on Resource-Aware Agentic AI},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2608.00685},
      arxiv = {arXiv:2608.00685},
      primaryclass = {cs.AI},
      author = {Leins, Nicolas and Pelleriti, Nico and Gonnermann-Müller, Jana and Pokutta, Sebastian},
      title = {When Does LLM Orchestration Pay Off? A Controlled Evaluation of Accuracy, Resources, and Task Difficulty}
    }
  4. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? Accepted at NeurIPS 2026 Workshop on Self-Evolving Diversity-Driven Search for Robust AI Systems. [arXiv]
    [BibTeX]
    @misc{2026_PelleritiEtAl_Evotrace_2605-20086:1,
      howpublished = {Accepted at NeurIPS 2026 Workshop on Self-Evolving Diversity-Driven Search for Robust AI Systems},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2605.20086},
      arxiv = {arXiv:2605.20086},
      primaryclass = {cs.NE},
      author = {Pelleriti, Nico and Nelaturu, Sree Harsha and Zhou, Zhanke and Li, Zongze and Zimmer, Max and Han, Bo and Pokutta, Sebastian},
      title = {What Do Evolutionary Coding Agents Evolve?}
    }
  5. Pelleriti, N., Kraus, N., May, A., and Pokutta, S. (2026). CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research. Accepted at NeurIPS 2026 Workshop on SaTQuML: Secure and Trustworthy Quantum Machine Learning.
    [BibTeX]
    @misc{2026_PelleritiKrausMayPokutta_CryptHarness,
      howpublished = {Accepted at NeurIPS 2026 Workshop on SaTQuML: Secure and Trustworthy Quantum Machine Learning},
      year = {2026},
      author = {Pelleriti, Nico and Kraus, Nicolai and May, Alexander and Pokutta, Sebastian},
      title = {CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research}
    }
  6. Pelleriti, N., Kraus, N., May, A., and Pokutta, S. (2026). CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research. Accepted at Third Workshop on Agents in the Wild: Safety, Security, and Beyond @ NeurIPS 2026.
    [BibTeX]
    @misc{2026_PelleritiKrausMayPokutta_CryptHarness:1,
      howpublished = {Accepted at Third Workshop on Agents in the Wild: Safety, Security, and Beyond @ NeurIPS 2026},
      year = {2026},
      author = {Pelleriti, Nico and Kraus, Nicolai and May, Alexander and Pokutta, Sebastian},
      title = {CryptHarness: A Harness for Agent-Assisted Cryptanalytic Research}
    }
  7. Pelleriti, N., Mundinger, K., Zimmer, M., and Pokutta, S. (2026). Zero: A Meta-Agent for Mathematical Research. Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026.
    [BibTeX]
    @misc{2026_PelleritiMundingerZimmerPokutta_Zero,
      howpublished = {Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026},
      year = {2026},
      author = {Pelleriti, Nico and Mundinger, Konrad and Zimmer, Max and Pokutta, Sebastian},
      title = {Zero: A Meta-Agent for Mathematical Research}
    }
  8. Pelleriti, N., Mundinger, K., Zimmer, M., and Pokutta, S. (2026). Zero: A Meta-Agent for Mathematical Research. Accepted at First Workshop on Meta Agents: Managing Agents That Manage Agents @ NeurIPS 2026.
    [BibTeX]
    @misc{2026_PelleritiMundingerZimmerPokutta_Zero:1,
      howpublished = {Accepted at First Workshop on Meta Agents: Managing Agents That Manage Agents @ NeurIPS 2026},
      year = {2026},
      author = {Pelleriti, Nico and Mundinger, Konrad and Zimmer, Max and Pokutta, Sebastian},
      title = {Zero: A Meta-Agent for Mathematical Research}
    }
  9. Petit-Tichanné, U., Pelleriti, N., Zimmer, M., and Pokutta, S. (2026). Learning the Coefficients of the Standard Volatility Forecaster. Accepted at NeurIPS 2026 Workshop TS-LIMITS: Generalization for Time Series in Tight Settings: Latency, Inference, Memory, PrIvacy and SusTainability.
    [BibTeX]
    @misc{2026_PetitTichannePelleritiZimmerPokutta_Volatilityforecaster,
      howpublished = {Accepted at NeurIPS 2026 Workshop TS-LIMITS: Generalization for Time Series in Tight Settings: Latency, Inference, Memory, PrIvacy and SusTainability},
      year = {2026},
      author = {Petit-Tichanné, Ulysse and Pelleriti, Nico and Zimmer, Max and Pokutta, Sebastian},
      title = {Learning the Coefficients of the Standard Volatility Forecaster}
    }
  10. 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. Accepted at ICML 2026 Workshop on AI As a Tool for Mathematics, Computer Science, and Machine Learning. [arXiv]
    [BibTeX]
    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:1,
      howpublished = {Accepted at ICML 2026 Workshop on AI As a Tool for Mathematics, Computer Science, and Machine Learning},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks}
    }
  11. 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. Accepted at 3rd AI for Math Workshop: Toward Self-Evolving Scientific Agents @ ICML 2026. [arXiv]
    [BibTeX]
    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:2,
      howpublished = {Accepted at 3rd AI for Math Workshop: Toward Self-Evolving Scientific Agents @ ICML 2026},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks}
    }
  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. Accepted at NeurIPS 2026 Workshop on Towards Test-Time Continual Learning Agents. [arXiv]
    [BibTeX]
    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:3,
      howpublished = {Accepted at NeurIPS 2026 Workshop on Towards Test-Time Continual Learning Agents},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {AlphaDiana: A System for Evaluating Reasoning Agents}
    }
  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. Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026. [arXiv]
    [BibTeX]
    @misc{2026_ZhouEtAl_AlphaDianaVerifiableReasoning_2610-20675:4,
      howpublished = {Accepted at The Sixth Workshop on Mathematical Reasoning and AI @ NeurIPS 2026},
      year = {2026},
      archiveprefix = {arXiv},
      eprint = {2610.20675},
      arxiv = {arXiv:2610.20675},
      primaryclass = {cs.AI},
      author = {Zhou, Zhanke and Li, Zongze and Huang, Weikai and Li, Xuan and Cao, Chentao and Feng, Xiao and Lu, Xiangyu and Hu, Jinbo and Lu, Menghan and Xie, Yi and Pelleriti, Nico and Liu, Shiyang and Zimmer, Max and Miranda, Brando and Yao, Jiangchao and Liu, Bo and Koyejo, Sanmi and Pokutta, Sebastian and Han, Bo},
      title = {AlphaDiana: A System for Evaluating Reasoning Agents}
    }
  14. Kera, H., Pelleriti, N., Ishihara, Y., Zimmer, M., and Pokutta, S. (2025). Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms. Advances in Neural Information Processing Systems, 38, 10434–10476. Associated with NeurIPS 2025. DOI: 10.52202/085713-0319 [arXiv]
    [BibTeX]
    @inproceedings{2025_KeraEtAl_Transformeroracles_2505-23696,
      year = {2025},
      booktitle = {Advances in Neural Information Processing Systems},
      series = {Advances in Neural Information Processing Systems},
      volume = {38},
      publisher = {Curran Associates},
      month = sep,
      pages = {10434--10476},
      doi = {10.52202/085713-0319},
      archiveprefix = {arXiv},
      eprint = {2505.23696},
      arxiv = {arXiv:2505.23696},
      primaryclass = {cs.LG},
      author = {Kera, Hiroshi and Pelleriti, Nico and Ishihara, Yuki and Zimmer, Max and Pokutta, Sebastian},
      title = {Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms}
    }
  15. Pelleriti, N., Zimmer, M., Wirth, E., and Pokutta, S. (2025). Approximating Latent Manifolds in Neural Networks via Vanishing Ideals. Proceedings of the 42nd International Conference on Machine Learning, 267. Associated with ICML 2025. [arXiv]
    [BibTeX]
    @inproceedings{2025_PelleritiZimmerWirthPokutta_Latentmanifolds,
      year = {2025},
      booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
      series = {Proceedings of Machine Learning Research},
      volume = {267},
      month = may,
      archiveprefix = {arXiv},
      eprint = {2502.15051},
      arxiv = {arXiv:2502.15051},
      primaryclass = {cs.LG},
      author = {Pelleriti, Nico and Zimmer, Max and Wirth, Elias and Pokutta, Sebastian},
      title = {Approximating Latent Manifolds in Neural Networks via Vanishing Ideals}
    }

Projects

AgentMath MATH+ EF-LiOpt-3
Agentic AI in Mathematics

This project aims to develop agentic AI systems for mathematical research: autonomous discovery of patterns and conjectures, design and execution of computational experiments, and integration with formal verification tools.

AgentMath MATH+ EF-LiOpt-3
Sep 2025 to Aug 2028
3
10

Talks and posters

Conference and workshop talks

Sep 2026
Workflow Selection for Lean Formalization by Nico Pelleriti
IOL @ Speinshart Scientific Center for AI and SuperTech, Speinshart
Jul 2026
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning by Nico Pelleriti
AI4Research Workshop, Seoul

Research seminar talks

Jul 2026
Frontier Systems for Scientific Discovery at Scale by Nico Pelleriti
Hong Kong Baptist University, Hong Kong
Apr 2026
Towards Open-Ended Scientific Discovery with Agentic AI by Nico Pelleriti
Zuse Institute Berlin, Berlin

Poster presentations

Jul 2026
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning by Nico Pelleriti
AI4Math Workshop, Seoul
Jul 2026
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning by Nico Pelleriti
AI4Research Workshop, Seoul
Apr 2026
Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers by Nico Pelleriti
14th International Conference on Learning Representations (ICLR), Rio de Janeiro
Dec 2025
Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms by Nico Pelleriti
39th conference on neural information processing systems (NeurIPS), San Diego
Jul 2025
Approximating Latent Manifolds in Neural Networks via Vanishing Ideals by Nico Pelleriti and Max Zimmer
42nd International Conference on Machine Learning (ICML), Vancouver

Events