3 papers
cs.AI2026
ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning
Xiuhui You, Jiayi Luo, Zichao Shen +2
Historical tool-use trajectories provide valuable experience for large language model (LLM) agents to plan and coordinate tool usage. Existing approaches directly construct tool-le…
cs.RO2025
SDA-PLANNER: State-Dependency Aware Adaptive Planner for Embodied Task Planning
Zichao Shen, Chen Gao, Jiaqi Yuan +3
Embodied task planning requires agents to produce executable actions in a close-loop manner within the environment. With progressively improving capabilities of LLMs in task decomp…
cs.AI2024
Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs
Zichao Shen, Tianchen Zhu, Qingyun Sun +2
Reinforcement learning (RL) faces challenges in evaluating policy trajectories within intricate game tasks due to the difficulty in designing comprehensive and precise reward funct…