Ax Ken M. Nakanishi 4/7/2026

Screening Is Enough

Multiscreen attention mechanism for language models. Introduces absolute query-key relevance to reject irrelevant keys, addressing softmax attention limitations.

Ax Xiaofan Zhou, Huy Nguyen, Bo Yu, Chenxi Liu, Lu Cheng 4/7/2026

Adaptive Stopping for Multi-Turn LLM Reasoning

Adaptive stopping mechanism for multi-turn LLM reasoning. Determines optimal stopping points for agents using retrieval-augmented generation and ReAct-style interactions.

Ax Zirui Zhao, Jun Hao Liew, Yan Yang, Wenzhuo Yang, Ziyang Luo, Doyen Sahoo, Silvio Savarese, Junnan Li 4/7/2026

GPA: Learning GUI Process Automation from Demonstrations

Vision-based robotic process automation (RPA) using sequential Monte Carlo localization. Enables stable GUI automation from single demonstrations with improved robustness.

Ax Dun Yuan, Fuyuan Lyu, Ye Yuan, Weixu Zhang, Bowei He, Jiayi Geng, Linfeng Du, Zipeng Sun, Yankai Chen, Changjiang Han, Jikun Kang, Alex Chen, Haolun Wu, Xue Liu 4/7/2026

Beyond Message Passing: A Semantic View of Agent Communication Protocols

Framework for analyzing agent communication protocols across three layers: communication, syntactic, and semantic. Systematically studies 18 representative protocols for LLM systems.

Ax Xun Sun, Baiheng Xie, Li Huang, Qiang Gao 4/7/2026

Scaling DPPs for RAG: Density Meets Diversity

Method scaling determinantal point processes for RAG systems to improve diversity of retrieved context while maintaining relevance.

Ax Lin Wang, Junfeng Fang, Dan Zhang, Fei Shen, Xiang Wang, Tat-Seng Chua 4/7/2026

DRAFT: Task Decoupled Latent Reasoning for Agent Safety

Framework for monitoring safety of tool-using LLM agents through latent reasoning that decouples safety judgment into trainable stages.

Ax William Merrill, Yanhong Li, Tyler Romero, Anej Svete, Caia Costello, Pradeep Dasigi, Dirk Groeneveld, David Heineman, Bailey Kuehl, Nathan Lambert, Chuan Li, Kyle Lo, Saumya Malik, DJ Matusz, Benjamin Minixhofer, Jacob Morrison, Luca Soldaini, Finbarr Timbers, Pete Walsh, Noah A. Smith, Hannaneh Hajishirzi, Ashish Sabharwal 4/7/2026

Olmo Hybrid: From Theory to Practice and Back

OLMo Hybrid: theoretical and empirical analysis of hybrid models combining linear RNNs and attention as alternatives to pure transformers with scaling benefits.

Ax David Sewell, Xingjian Li, Stepan Tretiakov, Krishna Kumar, David Fridovich-Keil 4/7/2026

Neural Operators for Multi-Task Control and Adaptation

Neural operator methods for multi-task optimal control problems, mapping task descriptions to control policies using permutation-invariant architectures.

Ax Wenjing Gong, Udbhav Srivastava, Yuchen Wang, Yuhao Jia, Qifan Wu, Weishan Bai, Yifan Yang, Xiao Huang, Xinyue Ye 4/7/2026

Earth Embeddings Reveal Diverse Urban Signals from Space

Benchmark of Earth embedding models (AlphaEarth, Prithvi, Clay) for neighborhood-scale urban monitoring from satellite imagery.

Ax Haocheng Ju, Guoxiong Gao, Jiedong Jiang, Bin Wu, Zeming Sun, Leheng Chen, Yutong Wang, Yuefeng Wang, Zichen Wang, Wanyi He, Peihao Wu, Liang Xiao, Ruochuan Liu, Bryan Dai, Bin Dong 4/7/2026

Automated Conjecture Resolution with Formal Verification

Framework for automated mathematical conjecture resolution combining LLMs with formal verification to improve reliability of research-level mathematical problem solving.

Ax Xiwen Chen, Jingjing Wang, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hejian Sang, Zhipeng Wang, Alborz Geramifard, Feng Luo 4/7/2026

SODA: Semi On-Policy Black-Box Distillation for Large Language Models

SODA: Semi on-policy knowledge distillation method for LLMs balancing off-policy simplicity with on-policy effectiveness without adversarial training instability.

Ax Shenzhi Yang, Guangcheng Zhu, Bowen Song, Sharon Li, Haobo Wang, Xing Zheng, Yingfan Ma, Zhongqi Chen, Weiqiang Wang, Gang Chen 4/7/2026

Can LLMs Learn to Reason Robustly under Noisy Supervision?

Analysis of LLM reasoning models under noisy labels in reinforcement learning with verifiable rewards, identifying label noise vulnerabilities.

Ax Haonian Ji, Kaiwen Xiong, Siwei Han, Peng Xia, Shi Qiu, Yiyang Zhou, Jiaqi Liu, Jinlong Li, Bingzhou Li, Zeyu Zheng, Cihang Xie, Huaxiu Yao 4/7/2026

ClawArena: Benchmarking AI Agents in Evolving Information Environments

ClawArena benchmark for evaluating AI agents in dynamic environments with evolving information, contradictions, and implicit user feedback.