Ax Shuzheng Si, Haozhe Zhao, Yu Lei, Qingyi Wang, Dingwei Chen, Zhitong Wang, Zhenhailong Wang, Kangyang Luo, Zheng Wang, Gang Chen, Fanchao Qi, Minjia Zhang, Maosong Sun 5/1/2026

From Context to Skills: Can Language Models Learn from Context Skillfully?

Investigates how LLMs learn from context by extracting rules into natural-language skills. Addresses challenges in inference-time skill augmentation for reasoning over complex contexts.

Ax Chao Fei, Hongcheng Guo, Yanghua Xiao 5/1/2026

When Agents Evolve, Institutions Follow

Multi-agent systems research drawing parallels between LLM-based agents and institutional governance, addressing coordination problems in complex societies.

Ax Binyan Xu, Xilin Dai, Kehuan Zhang 5/1/2026

Contextual Agentic Memory is a Memo, Not True Memory

Conceptual analysis arguing that current agentic memory systems implement lookup rather than true memory, with implications for agent capability and learning.

Ax Vishnuprasadh Kumaravelu, Sunil Gupta, P. K. Srijith 5/1/2026

Post-Optimization Adaptive Rank Allocation for LoRA

PARA: data-free compression method for LoRA that adaptively allocates ranks across model layers to reduce parameter redundancy in foundation model fine-tuning.

Ax Sukesh Subaharan, Venkatesan VS, Murugadasan P, Sivakumar D, Gautham N, Ganeshkumar M 5/1/2026

Modeling Clinical Concern Trajectories in Language Model Agents

LLM agent framework for clinical settings modeling concern trajectories with explicit state dynamics to surface pre-escalation signals without delegating medical authority.

Ax Junan Hu, Jian Liu, Jingxiang Lai, Jiarui Hu, Yiwei Sheng, Shuang Chen, Jian Li, Dazhao Du, Song Guo 5/1/2026

GUI Agents with Reinforcement Learning: Toward Digital Inhabitants

Comprehensive overview of GUI agents enhanced with reinforcement learning for long-horizon automation tasks, handling credit assignment and safe exploration in interactive environments.

Ax Habtom Kahsay Gidey, Alexander Lenz, Alois Knoll 5/1/2026

A Pattern Language for Resilient Visual Agents

Architectural pattern language for integrating vision language action models into enterprise systems, balancing latency and determinism requirements.