1 citations · 1 across the 8 of their papers we have counts for
9 papers
OptiMAS: Automatically Optimize Multi-Agent System
Yuxin Cheng, Chang Liu, Hanxin Yu +9
Automated evolution of Multi-Agent Systems (MAS) holds significant potential for reducing the manual effort required to design and optimize LLM-based agent architectures. However,…
Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents
AIMAE Team, Tianxiang Chen, Yan Cheng +39
Browser agents perform well on short, clean demonstrations, but real deployment is fundamentally different: agents must sustain dozens of decisions on live websites while recoverin…
SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
Chang Liu, Yuqi Zhang, Yiman Zhong +3
Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Existing agent skills are primari…
ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy
Xinkui Zhao, Sai Liu, Yifan Zhang +6
Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle wi…
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
Yangyi Fang, Jiaye Lin, Xiaoliang Fu +4
Multi-turn LLM agents are becoming pivotal to production systems, spanning customer service automation, e-commerce assistance, and interactive task management, where accurately dis…
Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
Yun Qu, Yuhang Jiang, Boyuan Wang +4
Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in…
Falcon-UI: Understanding GUI Before Following User Instructions
Huawen Shen, Chang Liu, Gengluo Li +4
Pursuing human-like interaction for Graphical User Interface (GUI) agents requires understanding the GUI context and following user instructions. However, existing works typically…
Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exploration
Yun Qu, Boyuan Wang, Yuhang Jiang +7
With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning. Although pursuing novelty, diversity, or uncertain…
LLM-Empowered State Representation for Reinforcement Learning
Boyuan Wang, Yun Qu, Yuhang Jiang +4
Conventional state representations in reinforcement learning often omit critical task-related details, presenting a significant challenge for value networks in establishing accurat…