Ax Shen Zhou Hong, Alex Kleinman, Alyssa Mathiowetz, Adam Howes, Julian Cohen, Suveer Ganta, Alex Letizia, Dora Liao, Deepika Pahari, Xavier Roberts-Gaal, Luca Righetti, Joe Torres 2/19/2026

Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology

RCT measuring whether LLM assistance improves novice performance in biology laboratory tasks and dual-use skill acquisition.

Ax Nils Palumbo, Sarthak Choudhary, Jihye Choi, Prasad Chalasani, Mihai Christodorescu, Somesh Jha 2/19/2026

Policy Compiler for Secure Agentic Systems

Policy compiler providing deterministic enforcement of authorization policies for LLM-based agents with information flow tracking.

Ax Aaron Bell, Amit Aides, Amr Helmy, Arbaaz Muslim, Aviad Barzilai, Aviv Slobodkin, Bolous Jaber, David Schottlander, George Leifman, Joydeep Paul, Mimi Sun, Nadav Sherman, Natalie Williams, Per Bjornsson, Roy Lee, Ruth Alcantara, Thomas Turnbull, Tomer Shekel, Vered Silverman, Yotam Gigi, Adam Boulanger, Alex Ottenwess, Ali Ahmadalipour, Anna Carter, Behzad Vahedi, Charles Elliott, David Andre, Elad Aharoni, Gia Jung, Hassler Thurston, Jacob Bien, Jamie McPike, Jessica Sapick, Juliet Rothenberg, Kartik Hegde, Kel Markert, Kim Philipp Jablonski, Luc Houriez, Monica Bharel, Phing VanLee, Reuven Sayag, Sebastian Pilarski, Shelley Cazares, Shlomi Pasternak, Siduo Jiang, Thomas Colthurst, Yang Chen, Yehonathan Refael, Yochai Blau, Yuval Carny, Yael Maguire, Avinatan Hassidim, James Manyika, Tim Thelin, Genady Beryozkin, Gautam Prasad, Luke Barrington, Yossi Matias, Niv Efron, Shravya Shetty 2/19/2026

Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning

Geospatial AI foundation models with agentic reasoning for analyzing large-scale satellite and environmental data.

Ax Maohao Ran, Zhenglin Wan, Cooper Lin, Yanting Zhang, Hongyu Xin, Hongwei Fan, Yibo Xu, Beier Luo, Yaxin Zhou, Wangbo Zhao, Lijie Yang, Lang Feng, Fuchao Yang, Jingxuan Wu, Yiqiao Huang, Chendong Ma, Dailing Jiang, Jianbo Deng, Sihui Han, Yang You, Bo An, Yike Guo, Jun Song 2/19/2026

CaveAgent: Transforming LLMs into Stateful Runtime Operators

Framework transforming LLMs into stateful runtime operators via dual-stream architecture to handle complex long-horizon tasks with better state management.

Ax Haibo Tong, Feifei Zhao, Linghao Feng, Ruoyu Wu, Ruolin Chen, Lu Jia, Zhou Zhao, Jindong Li, Tenglong Li, Erliang Lin, Shuai Yang, Enmeng Lu, Yinqian Sun, Qian Zhang, Zizhe Ruan, Jinyu Fan, Zeyang Yue, Ping Wu, Huangrui Li, Chengyi Sun, Yi Zeng 2/19/2026

ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI

AI safety evaluation framework addressing frontier risks and systemic challenges in increasingly autonomous AI systems with unpredictable behaviors.

Ax Tim R. Davidson, Veniamin Veselovsky, Martin Josifoski, Maxime Peyrard, Antoine Bosselut, Michal Kosinski, Robert West 2/19/2026

Evaluating Language Model Agency through Negotiations

Evaluation framework using negotiation games to assess language model agency through multi-turn interactions and complex reasoning scenarios.

Ax Ruichuan An, Sihan Yang, Renrui Zhang, Ming Lu, Tianyi Jiang, Kai Zeng, Yulin Luo, Jiajun Cao, Hao Liang, Ying Chen, Qi She, Shanghang Zhang, Wentao Zhang 2/19/2026

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Multi-concept personalization approach for vision-language models, enabling understanding of multiple user-provided concepts and their interactions.

Ax K. J. Kevin Feng, Kevin Pu, Matt Latzke, Tal August, Pao Siangliulue, Jonathan Bragg, Daniel S. Weld, Amy X. Zhang, Joseph Chee Chang 2/19/2026

Cocoa: Co-Planning and Co-Execution with AI Agents

Framework enabling human-agent co-planning and co-execution, allowing deeper collaboration in long-running AI agent tasks beyond autonomous workflows.

Ax Veeti Ahvonen, Maurice Funk, Damian Heiman, Antti Kuusisto, Carsten Lutz 2/19/2026

Expressive Power of Graph Transformers via Logic

Theoretical analysis of graph transformers' expressive power using logic, covering both real numbers and floating-point settings.