DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems.

Thomas Foster

Willem Röpke Samuel Coward Andrei Lupu Thomas Foster Tim Rocktäschel Jakob N. Foerster DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems. 2026 January abs/2601.01931 CoRR https://doi.org/10.48550/arXiv.2601.01931 db/journals/corr/corr2601.html#abs-2601-01931 streams/journals/corr

Alisia Maria Lupidi Bhavul Gauri Thomas Foster Bassel Al Omari Despoina Magka Alberto Pepe Alexis Audran-Reiss Muna Aghamelu Nicolas Mario Baldwin Lucia Cipolina-Kun Jean-Christophe Gagnon-Audet Chee Hau Leow Sandra Lefdal Hossam Mossalam Abhinav Moudgil Saba Nazir Emanuel Tewolde Isabel Urrego Jordi Armengol-Estapé Amar Budhiraja Gaurav Chaurasia Abhishek Charnalia Derek Dunfield Karen Hambardzumyan Daniel Izcovich Martin Josifoski Ishita Mediratta Kelvin Niu Parth Pathak Michael Shvartsman Edan Toledo Anton Protopopov Roberta Raileanu Alexander H. Miller Tatiana Shavrina Jakob N. Foerster Yoram Bachrach AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents. 2026 February abs/2602.06855 CoRR https://doi.org/10.48550/arXiv.2602.06855 db/journals/corr/corr2602.html#abs-2602-06855 streams/journals/corr

William Lugoloobi Thomas Foster William Bankes Chris Russell 0001 LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations. 2026 February abs/2602.09924 CoRR https://doi.org/10.48550/arXiv.2602.09924 db/journals/corr/corr2602.html#abs-2602-09924 streams/journals/corr

Thomas Foster Jakob N. Foerster Learning to Reason at the Frontier of Learnability. 2025 February abs/2502.12272 CoRR https://doi.org/10.48550/arXiv.2502.12272 db/journals/corr/corr2502.html#abs-2502-12272 streams/journals/corr

Bingchen Zhao Despoina Magka Minqi Jiang Xian Li Roberta Raileanu Tatiana Shavrina Jean-Christophe Gagnon-Audet Kelvin Niu Shagun Sodhani Michael Shvartsman Andrei Lupu Alisia Maria Lupidi Edan Toledo Karen Hambardzumyan Martin Josifoski Thomas Foster Lucia Cipolina-Kun Abhishek Charnalia Derek Dunfield Alexander H. Miller Oisin Mac Aodha Jakob N. Foerster Yoram Bachrach The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements. 2025 June abs/2506.22419 CoRR https://doi.org/10.48550/arXiv.2506.22419 db/journals/corr/corr2506.html#abs-2506-22419 streams/journals/corr

Dulhan Jayalath Shashwat Goel Thomas Foster Parag Jain Suchin Gururangan Cheng Zhang Anirudh Goyal Alan Schelten Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision. 2025 September abs/2509.14234 CoRR https://doi.org/10.48550/arXiv.2509.14234 db/journals/corr/corr2509.html#abs-2509-14234 streams/journals/corr

Andrew M. Bean Ryan Othniel Kearns Angelika Romanou Franziska Sofia Hafner Harry Mayne Jan Batzner Negar Foroutan Chris Schmitz Karolina Korgul Hunar Batra Oishi Deb Emma Beharry Cornelius Emde Thomas Foster Anna Gausen María Grandury Simeng Han Valentin Hofmann Lujain Ibrahim Hazel Kim Hannah Rose Kirk Fangru Lin Gabrielle Kaili-May Liu Lennart Luettgau Jabez Magomere Jonathan Rystrøm Anna Sotnikova Yushi Yang Yilun Zhao 0001 Adel Bibi Antoine Bosselut Ronald Clark Arman Cohan Jakob N. Foerster Yarin Gal Scott A. Hale Inioluwa Deborah Raji Christopher Summerfield Philip H. S. Torr Cozmin Ududec Luc Rocher Adam Mahdi Measuring what Matters: Construct Validity in Large Language Model Benchmarks. 2025 November abs/2511.04703 CoRR https://doi.org/10.48550/arXiv.2511.04703 db/journals/corr/corr2511.html#abs-2511-04703 streams/journals/corr

Thomas Foster Ioana Croitoru Robert Dorfman Christoffer Edlund Thomas Varsavsky Jon Almazán Flexible visual prompts for in-context learning in computer vision. 2023 abs/2312.06592 CoRR https://doi.org/10.48550/arXiv.2312.06592 db/journals/corr/corr2312.html#abs-2312-06592

Thomas Foster Chon Lok Lei Martin Robinson David Gavaghan Ben Lambert Model Evidence with Fast Tree Based Quadrature. 2020 abs/2005.11300 CoRR https://arxiv.org/abs/2005.11300 db/journals/corr/corr2005.html#abs-2005-11300

Hoh Peter In Thomas Foster Jason Surprise Sung-Oh David Jung Dick B. Simmons Hiroko Fujihara Web-Based Feature Reduction System: A Case Study. 406-409 2003 conf/saint/2003 SAINT https://doi.org/10.1109/SAINT.2003.1183085 https://doi.ieeecomputersociety.org/10.1109/SAINT.2003.1183085 db/conf/saint/saint2003.html#InFSJSF03 Muna Aghamelu Jon Almazán Oisin Mac Aodha Jordi Armengol-Estapé Alexis Audran-Reiss Yoram Bachrach Nicolas Mario Baldwin William Bankes Hunar Batra Jan Batzner Andrew M. Bean Emma Beharry Adel Bibi Antoine Bosselut Amar Budhiraja Abhishek Charnalia Gaurav Chaurasia Lucia Cipolina-Kun Ronald Clark Arman Cohan Samuel Coward Ioana Croitoru Oishi Deb Robert Dorfman Derek Dunfield Christoffer Edlund Negar Foroutan EghlidiNegar Foroutan Cornelius Emde Jakob N. Foerster Hiroko Fujihara Jean-Christophe Gagnon-Audet Yarin Gal Bhavul Gauri Anna Gausen David Gavaghan Shashwat Goel Anirudh Goyal María Grandury Suchin Gururangan Franziska Sofia Hafner Scott A. Hale Karen Hambardzumyan Simeng Han Valentin Hofmann Lujain Ibrahim Hoh Peter In Daniel Izcovich Parag Jain Dulhan Jayalath Minqi Jiang Martin Josifoski Sung-Oh David Jung Ryan Othniel Kearns Hazel Kim Hannah KirkHannah Rose Kirk Karolina Korgul Ben Lambert Sandra Lefdal Chon Lok Lei Chee Hau Leow Xian Li Fangru Lin Gabrielle K. LiuGabrielle Kaili-May Liu Lennart Luettgau William Lugoloobi Alisia Maria Lupidi Andrei Lupu Despoina Magka Jabez Magomere Adam Mahdi Harry Mayne Ishita Mediratta Alexander H. Miller Hossam Mossalam Abhinav Moudgil Saba Nazir Kelvin Niu Bassel Al Omari Parth Pathak Alberto Pepe Anton Protopopov Roberta Raileanu Inioluwa Deborah Raji Martin Robinson Luc Rocher Tim Rocktäschel Angelika Romanou Willem Röpke Chris Russell 0001 Jonathan Rystrøm Alan Schelten Chris Schmitz Tatiana Shavrina Michael Shvartsman Dick B. Simmons Shagun Sodhani Anna Sotnikova Christopher Summerfield Jason Surprise Emanuel Tewolde Edan Toledo Philip Torr 0001Philip H. S. Torr Cozmin Ududec Isabel Urrego Thomas Varsavsky Yushi Yang Cheng Zhang Bingchen Zhao Yilun Zhao 0001