Ax Jiajun Zhou, Wei Shao, Lingchao Zheng, Yuwei Fan, Ngai Wong 5/15/2026

AIS: Adaptive Importance Sampling for Quantized RL

Adaptive importance sampling method to address rollout-training mismatch in low-precision RL for LLMs, preventing policy gradient bias and training collapse.

Ax Valliappan Chidambaram Adaikkappan, Vincent Martineau, Joshua Romoff, David Meger 5/15/2026

CA2: Code-Aware Agent for Automated Game Testing

AI agent using call stack information to automate game testing with improved code coverage beyond RL baselines.

Ax Nilay Patel, Noah Arias, Davit Babayan, Victoria Cochran, Timothy Libman, Hafsah Mahmood, Liam McCarty, Soli Munoz, Laurel Willey, Jeffrey Flanigan 5/15/2026

MathAtlas: A Benchmark for Autoformalization in the Wild

Large-scale autoformalization benchmark with 52k graduate-level math theorems, definitions, and proofs from 103 textbooks.

Ax Benjamin Schneider, Xavier Schneider, Victor Zhong, Sun Sun 5/15/2026

ASH: Agents that Self-Hone via Embodied Learning

ASH system that learns embodied policies for long-horizon tasks from unlabeled internet video through self-improvement loops and inverse dynamics models.

Ax Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar, Nanyun Peng, Vishy Tirumalashetty, Chun-Liang Li, Rui Zhang, Jinsung Yoon, Tomas Pfister 5/15/2026

Nexus : An Agentic Framework for Time Series Forecasting

Nexus agentic framework for time series forecasting integrating LLMs with specialized foundation models using contextual textual signals.

Ax Avik Bhattacharya, Siddhant Dnyanesh Gole, Subhasis Chaudhuri, Alejandro C. Frery, Biplab Banerjee 5/15/2026

ArcGate: Adaptive Arctangent Gated Activation

ArcGate activation function with learnable parameters offering adaptive non-linear transformations for deep networks.