Work

Prime Intellect blog

Papers

2026

  • MirrorCode: AI Can Rebuild Entire Programs From Behavior Alone[PDF] [] [Website]
    @misc{adamczewski2026mirrorcode,
      title={MirrorCode: AI Can Rebuild Entire Programs From Behavior Alone},
      author={Tom Adamczewski and David Owen and David Rein and Florian Brand and Giles Edkins and Allen Hart and Daniel O'Connell},
      year={2026},
      url={https://epoch.ai/MirrorCode},
    }
    
  • The ATOM Report: Measuring the Open Language Model Ecosystem[PDF] [] [Website]
    @misc{lambert2026atomreportmeasuringopen,
      title={The ATOM Report: Measuring the Open Language Model Ecosystem},
      author={Nathan Lambert and Florian Brand},
      year={2026},
      eprint={2604.07190},
      archivePrefix={arXiv},
      primaryClass={cs.CY},
      url={https://arxiv.org/abs/2604.07190},
    }
    

2025

  • EXAR: A Unified Experience-Grounded Agentic Reasoning Architecture[PDF] []
    @inproceedings{Bergmann2025EXARUnifiedExperienceGrounded,
      title = {{EXAR: A Unified Experience-Grounded Agentic Reasoning Architecture}},
      booktitle = {{Case-Based Reasoning Research and Development - 33rd International Conference, {ICCBR} 2025, Biarritz, France, June 30 - July 3, 2025, Proceedings}},
      author = {Bergmann, Ralph and Brand, Florian and Lenz, Mirko and Malburg, Lukas},
      pages        = {3--17},
      volume       = {15662},
      editor = {Bichindaritz, Isabelle and Lopez, Beatriz},
      publisher    = {Springer.},
      doi          = {10.1007/978-3-031-96559-3\_1},
      year         = {2025},
      url = {https://www.wi2.uni-trier.de/shared/publications/2025_ICCBR_EXAR_BergmannEtAL.pdf}
    }
    
  • ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models[PDF] [] [Blog]
    @misc{claviƩ2025readbenchmeasuringdensetext,
      title={ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models}, 
      author={Benjamin ClaviƩ and Florian Brand},
      year={2025},
      eprint={2505.19091},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.19091}, 
    }
    
  • Case-Based Reasoning Meets Large Language Models: A Research Manifesto For Open Challenges and Research Directions[PDF] []
    @unpublished{bachCaseBasedReasoningMeets2025,
      title        = {{Case-Based Reasoning Meets Large Language Models: A Research Manifesto For Open Challenges and Research Directions}},
      author       = {Bach, Kerstin and Bergmann, Ralph and Brand, Florian and others},
      year         = 2025,
      note         = {working paper or preprint},
      pdf          = {https://hal.science/hal-05006761v1/file/main.pdf},
      hal_id       = {hal-05006761},
      hal_version  = {v1}
    }
    

2024

  • Large Language Models as Knowledge Engineers[PDF] []
    @inproceedings{brandLargeLanguageModels2024,
      title        = {Large Language Models as Knowledge Engineers},
      author       = {Florian Brand and Lukas Malburg and Ralph Bergmann},
      year         = 2024,
      booktitle    = {Proceedings of the Workshops at the 32nd International Conference on Case-Based Reasoning {(ICCBR-WS} 2024) co-located with the 32nd International Conference on Case-Based Reasoning {(ICCBR} 2024), M{\\'e}rida, Mexico, July 1, 2024},
      publisher    = {CEUR-WS.org},
      series       = {{CEUR} Workshop Proceedings},
      volume       = 3708,
      pages        = {3--18},
      timestamp    = {Tue, 25 Jun 2024 16:52:02 +0200},
      biburl       = {https://dblp.org/rec/conf/iccbr/BrandMB24.bib},
      bibsource    = {dblp computer science bibliography, https://dblp.org}
    }
    

2023

  • Using Deep Reinforcement Learning for the Adaptation of Semantic Workflows[PDF] []
    @inproceedings{brandUsingDeepReinforcement2023,
      title        = {Using Deep Reinforcement Learning for the Adaptation of Semantic Workflows},
      author       = {Florian Brand and Katharina Lott and Lukas Malburg and Maximilian Hoffmann and Ralph Bergmann},
      year         = 2023,
      booktitle    = {Proceedings of the Workshops at the 31st International Conference on Case-Based Reasoning {(ICCBR-WS} 2023) co-located with the 31st International Conference on Case-Based Reasoning {(ICCBR} 2023), Aberdeen, Scotland, UK, July 17, 2023},
      publisher    = {CEUR-WS.org},
      series       = {{CEUR} Workshop Proceedings},
      volume       = 3438,
      pages        = {55--70},
      timestamp    = {Tue, 11 Jul 2023 17:14:10 +0200},
      biburl       = {https://dblp.org/rec/conf/iccbr/BrandLM0B23.bib},
      bibsource    = {dblp computer science bibliography, https://dblp.org}
    }
    
  • Adaptive Management of Cyber-Physical Workflows by Means of Case-Based Reasoning and Automated Planning[PDF] []
    @inproceedings{malburgAdaptiveManagementCyber-Physical2022,
      title        = {Adaptive Management of Cyber-Physical Workflows by Means of Case-Based Reasoning and Automated Planning},
      author       = {Lukas Malburg and Florian Brand and Ralph Bergmann},
      year         = 2022,
      booktitle    = {Enterprise Design, Operations, and Computing. {EDOC} 2022 Workshops - IDAMS, SoEA4EE, TEAR, {EDOC} Forum, Demonstrations Track and Doctoral Consortium, Bozen-Bolzano, Italy, October 4-7, 2022, Revised Selected Papers},
      publisher    = {Springer},
      series       = {Lecture Notes in Business Information Processing},
      volume       = 466,
      pages        = {79--95},
      timestamp    = {Sat, 11 Mar 2023 00:11:50 +0100},
      biburl       = {https://dblp.org/rec/conf/edoc/MalburgBB22.bib},
      bibsource    = {dblp computer science bibliography, https://dblp.org}
    }