Ax Arushi Rai, Qiang Zhang, Hanqing Zeng, Yunkai Zhang, Dipesh Tamboli, Xiangjun Fan, Zhuokai Zhao 3/20/2026

TARo: Token-level Adaptive Routing for LLM Test-time Alignment

TARo enables frozen LLMs to perform structured reasoning at inference time through token-level adaptive routing, avoiding expensive post-training alignment.

Ax Huichi Zhou, Siyuan Guo, Anjie Liu, Zhongwei Yu, Ziqin Gong, Bowen Zhao, Zhixun Chen, Menglong Zhang, Yihang Chen, Jinsong Li, Runyu Yang, Qiangbin Liu, Xinlei Yu, Jianmin Zhou, Na Wang, Chunyang Sun, Jun Wang 3/20/2026

Memento-Skills: Let Agents Design Agents

Memento-Skills introduces an LLM agent that autonomously designs and improves task-specific agents through continual learning with stateful prompts and reusable skills.

Ax Huaide Jiang, Yash Chaudhary, Yuping Wang, Zehao Wang, Raghav Sharma, Manan Mehta, Yang Zhou, Lichao Sun, Zhiwen Fan, Zhengzhong Tu, Jiachen Li 3/20/2026

NavTrust: Benchmarking Trustworthiness for Embodied Navigation

NavTrust benchmark evaluates trustworthiness of embodied navigation agents under real-world corruptions in Vision-Language Navigation and Object-Goal Navigation tasks.

Ax \.Ilter Onat Korkmaz, Ya\c{s}ar Cahit Y{\i}ld{\i}r{\i}m, \c{C}a\u{g}{\i}n Ararat, Cem Tekin 3/20/2026

Vector Optimization with Gaussian Process Bandits

VOGP algorithm using Gaussian process bandits for black-box vector optimization with incomplete order relations and Pareto optimality guarantees.