activity
20242026
collaborators

10 papers

cs.AI2026

Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees

Yu Chen, Ruishuo Chen, Xun Wang +2

Loading reusable skill documents into a bounded context window is now the primary way large language model (LLM) agents acquire task-specific capabilities, which makes skill select…

cs.LG2026

MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models

Chenglin Liu, Xun Wang, Ruishuo Chen +2

Reward function design remains a bottleneck in reinforcement learning. While large language models (LLMs) have enabled automated reward generation, existing methods generate and re…

cs.AI2026

When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Conflict

Lu Yang, Shusheng Xu, Zhuoran Li +2

LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks…

cs.CV2026

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

Lingao Xiao, Yalun Dai, Yangyu Huang +17

Despite growing automation, turning a paper into a coherent poster, talk video, and blog piece often remains a labor-intensive last mile. Recent systems increasingly generate multi…

cs.LG2026

Reparameterization Flow Policy Optimization

Hai Zhong, Zhuoran Li, Xun Wang +1

Reparameterization Policy Gradient (RPG) has emerged as a powerful paradigm for model-based reinforcement learning, enabling high sample efficiency by backpropagating gradients thr…

cs.LG2025

From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos

Xun Wang, Zhuoran Li, Yanshan Lin +2

Training a team of agents from scratch in multi-agent reinforcement learning (MARL) is highly inefficient, much like asking beginners to play a symphony together without first prac…