9 papers
StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure
Wenyi Wu, Sibo Zhu, Kun Zhou +3
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use. However, real-world tasks are o…
Causally Debiased Latent Action Model for Embodied Action Conditioned World Models
Yufan Wei, Kun Zhou, Lingjun Mao +9
Action-conditioned world models (ACWMs) aim to simulate future observations conditioned on embodied actions, offering a promising foundation for robot planning, policy evaluation,…
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6
Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…
AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition
Jixuan Chen, Jianzhi Shen, Haoqiang Kang +10
LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffo…
Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
Wenyi Wu, Sibo Zhu, Kun Zhou +1
Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-ho…
C-World: A Computer Use Agent Environment Creator
Ziqiao Xi, Shuang Liang, Qi Liu +9
To close the gap between LLM-based agents and humans in planning and reasoning, agents need large-scale, diverse environments for continuous learning -- yet building such environme…