5 papers
FedQHD: Closed-Form Function-Space Federated Reinforcement Learning
Yuchen Hou, Yongshan Chen, Zhuowen Zou +4
Federated reinforcement learning enables decentralized agents to collaboratively improve policies or value estimates without exchanging raw trajectories. However, FedAvg-style para…
LangGap: Diagnosing and Closing the Language Gap in Vision-Language-Action Models
Yuchen Hou, Lin Zhao
Vision-Language-Action (VLA) models achieve over 95% success on standard benchmarks. However, through systematic experiments, we find that current state-of-the-art VLA models large…
AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios
Kaiyuan Chen, Qimin Wu, Taiyu Hou +42
The capacity of AI agents to effectively handle tasks of increasing duration and complexity continues to grow, demonstrating exceptional performance in coding, deep research, and c…
GNNs as Predictors of Agentic Workflow Performances
Yuanshuo Zhang, Yuchen Hou, Bohan Tang +4
Agentic workflows invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks. However, optimizing such workflows is costly and inefficient i…
Self-Evolving Multi-Agent Collaboration Networks for Software Development
Yue Hu, Yuzhu Cai, Yaxin Du +6
LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance…