LLMs versus the Halting Problem: Revisiting Program Termination Prediction.

Oren Sultan

Oren Sultan Jordi Armengol-Estapé Pascal Kesseli Julien Vanegue Dafna Shahaf Yossi Adi Peter W. O'Hearn LLMs versus the Halting Problem: Revisiting Program Termination Prediction. 2026 January abs/2601.18987 CoRR https://doi.org/10.48550/arXiv.2601.18987 db/journals/corr/corr2601.html#abs-2601-18987 streams/journals/corr

Oren Sultan Eitan Stern Dafna Shahaf Towards Reliable Proof Generation with LLMs: A Neuro-Symbolic Approach. 2025 May abs/2505.14479 CoRR https://doi.org/10.48550/arXiv.2505.14479 db/journals/corr/corr2505.html#abs-2505-14479 streams/journals/corr

FAIR CodeGen team Jade Copet Quentin Carbonneaux Gal Cohen Jonas Gehring Jacob Kahn Jannik Kossen Felix Kreuk Emily McMilin Michel Meyer Yuxiang Wei 0003 David Zhang Kunhao Zheng Jordi Armengol-Estapé Pedram Bashiri Maximilian Beck Pierre Chambon Abhishek Charnalia Chris Cummins Juliette Decugis Zacharias V. Fisches François Fleuret Fabian Gloeckle Alex Gu Michael Hassid Daniel Haziza Badr Youbi Idrissi Christian Keller Rahul Kindi Hugh Leather Gallil Maimon Aram H. Markosyan Francisco Massa Pierre-Emmanuel Mazaré Vegard Mella Naila Murray Keyur Muzumdar Peter W. O'Hearn Matteo Pagliardini Dmitrii Pedchenko Tal Remez Volker Seeker Marco Selvi Oren Sultan Sida Wang 0001 Luca Wehrstedt Ori Yoran Lingming Zhang 0001 Taco Cohen Yossi Adi Gabriel Synnaeve CWM: An Open-Weights LLM for Research on Code Generation with World Models. 2025 October abs/2510.02387 CoRR https://doi.org/10.48550/arXiv.2510.02387 db/journals/corr/corr2510.html#abs-2510-02387 streams/journals/corr

Oren Sultan Alexander Khasin Guy Shiran Asnat Greenstein-Messica Dafna Shahaf Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications. 1286-1304 2024 EMNLP (Industry Track) https://doi.org/10.18653/v1/2024.emnlp-industry.96 https://aclanthology.org/2024.emnlp-industry.96 conf/emnlp/2024i db/conf/emnlp/emnlp2024i.html#SultanKSGS24 Oren Sultan Yonatan Bitton Ron Yosef Dafna Shahaf ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies. 5900-5924 2024 NAACL-HLT https://doi.org/10.18653/v1/2024.naacl-long.329 conf/naacl/2024 db/conf/naacl/naacl2024.html#SultanBYS24

Oren Sultan Yonatan Bitton Ron Yosef Dafna Shahaf ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies. 2024 abs/2403.01139 CoRR https://doi.org/10.48550/arXiv.2403.01139 db/journals/corr/corr2403.html#abs-2403-01139

Oren Sultan Alex Khasin Guy Shiran Asnat Greenstein-Messica Dafna Shahaf Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications. 2024 abs/2410.02952 CoRR https://doi.org/10.48550/arXiv.2410.02952 db/journals/corr/corr2410.html#abs-2410-02952 streams/journals/corr

Oren Sultan Dafna Shahaf Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes. 3547-3562 2022 EMNLP https://doi.org/10.18653/v1/2022.emnlp-main.232 https://aclanthology.org/2022.emnlp-main.232 conf/emnlp/2022 db/conf/emnlp/emnlp2022.html#SultanS22 Kyle Richardson 0001 Ronen Tamari Oren Sultan Dafna Shahaf Reut Tsarfaty Ashish Sabharwal Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs. 9703-9719 2022 EMNLP https://doi.org/10.18653/v1/2022.emnlp-main.658 https://aclanthology.org/2022.emnlp-main.658 conf/emnlp/2022 db/conf/emnlp/emnlp2022.html#0001TSSTS22

Oren Sultan Dafna Shahaf Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes. 2022 abs/2210.12197 CoRR https://doi.org/10.48550/arXiv.2210.12197 db/journals/corr/corr2210.html#abs-2210-12197

Kyle Richardson 0001 Ronen Tamari Oren Sultan Reut Tsarfaty Dafna Shahaf Ashish Sabharwal Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs. 2022 abs/2211.07950 CoRR https://doi.org/10.48550/arXiv.2211.07950 db/journals/corr/corr2211.html#abs-2211-07950

Oren Sultan Rayen Dhahri Yauheni Mardan Tobias Eder Georg Groh From Judgement's Premises Towards Key Points. 2022 abs/2212.12238 CoRR https://doi.org/10.48550/arXiv.2212.12238 db/journals/corr/corr2212.html#abs-2212-12238

Yossi Adi Jordi Armengol-Estapé Pedram Bashiri Maximilian Beck Yonatan Bitton Quentin Carbonneaux Pierre Chambon Abhishek Charnalia Gal Cohen Taco Cohen Jade Copet Chris Cummins Juliette Decugis Rayen Dhahri Tobias Eder Zacharias V. Fisches François Fleuret Jonas Gehring Fabian Gloeckle Asnat Greenstein-Messica Georg Groh Alex Gu Michael Hassid Daniel Haziza Badr Youbi Idrissi Jacob Kahn Christian Keller Pascal Kesseli Alexander KhasinAlex Khasin Rahul Kindi Jannik Kossen Felix Kreuk Hugh Leather Gallil Maimon Yauheni Mardan Aram H. Markosyan Francisco Massa Pierre-Emmanuel Mazaré Emily McMilin Vegard Mella Michel Meyer Naila Murray Keyur Muzumdar Peter W. O'Hearn Matteo Pagliardini Dmitrii Pedchenko Tal Remez Kyle Richardson 0001 Ashish Sabharwal Volker Seeker Marco Selvi Dafna Shahaf Guy Shiran Eitan Stern Gabriel Synnaeve Ronen Tamari FAIR CodeGen team Reut Tsarfaty Julien Vanegue Sida I. WangSida Wang 0001 Luca Wehrstedt Yuxiang Wei 0003 Ori Yoran Ron Yosef David Zhang Lingming Zhang 0001 Kunhao Zheng