Ax Tian Qin, Felix Bai, Ting-Yao Hu, Raviteja Vemulapalli, Hema Swetha Koppula, Zhiyang Xu, Bowen Jin, Mert Cemri, Jiarui Lu, Zirui Wang, Meng Cao 4/20/2026

COMPASS: Benchmarking Constrained Optimization in LLM Agents

COMPASS benchmark evaluating LLM agents' ability to perform constrained optimization in multi-turn conversations for travel planning and scheduling tasks.

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 4/20/2026

Olmo Hybrid: From Theory to Practice and Back

Hybrid language models mixing RNNs and attention mechanisms, comparing performance advantages over pure transformers with theoretical and practical evidence.

Ax Mingchen Zhuge, Changsheng Zhao, Haozhe Liu, Zijian Zhou, Shuming Liu, Wenyi Wang, Ernie Chang, Gael Le Lan, Junjie Fei, Wenxuan Zhang, Yasheng Sun, Zhipeng Cai, Zechun Liu, Yunyang Xiong, Yining Yang, Yuandong Tian, Yangyang Shi, Vikas Chandra, J\"urgen Schmidhuber 4/20/2026

Neural Computers

Proposes Neural Computers that unify computation, memory, and I/O in learned runtime states, exploring general-purpose neural machine architectures.

Ax Mengxin Wang (Naveen Jindal School of Management, The University of Texas at Dallas), Dennis J. Zhang (Olin School of Business, Washington University in St. Louis), Heng Zhang (W. P. Carey School of Business, Arizona State University) 4/20/2026

Large Language Models for Market Research: A Data-augmentation Approach

Uses LLMs to generate synthetic data for market research and conjoint analysis, addressing scalability limitations of traditional surveys.

Ax Yuxuan Zhu, David H. Yang, Mohammad Mohammadi Amiri, Keerthiram Murugesan, Tejaswini Pedapati, Pin-Yu Chen 4/20/2026

OjaKV: Context-Aware Online Low-Rank KV Cache Compression

OjaKV compresses KV cache in long-context LLMs using context-aware online low-rank projection, reducing memory bottlenecks during inference.

Ax Victoria Ebert, Rishabh Singh, Tuochao Chen, Noah A. Smith, Shyamnath Gollakota 4/20/2026

Reading Between the Lines: The One-Sided Conversation Problem

Addresses one-sided conversation problem where only one speaker is recorded, reconstructing missing dialogue and generating summaries using conversational AI.

Ax Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang 4/20/2026

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation

Disco-RAG enhances RAG systems by incorporating discourse structure awareness, enabling LLMs to better synthesize knowledge from multiple retrieved passages.