7 papers
Exact Is Easier: Credit Assignment for Cooperative LLM Agents
Yanjun Chen, Yirong Sun, Hanlin Wang +5
Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts the result it claims to measure. This f…
Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents
Hanlin Wang, Chak Tou Leong, Jian Wang +1
Recent advancements in large language models (LLMs) have enabled agents to tackle complex embodied tasks through environmental interaction. However, these agents still make subopti…
Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
Zhen Liu, Xinyu Ning, Zhe Hu +8
Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows…
Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
Youwei Liu, Jian Wang, Hanlin Wang +2
Recent advances in world models have shown promise for modeling future dynamics of environmental states, enabling agents to reason and act without accessing real environments. Curr…
Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
Xinghao Chen, Anhao Zhao, Heming Xia +7
Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized…
STeCa: Step-level Trajectory Calibration for LLM Agent Learning
Hanlin Wang, Jian Wang, Chak Tou Leong +1
Large language model (LLM)-based agents have shown promise in tackling complex tasks by interacting dynamically with the environment. Existing work primarily focuses on behavior cl…