Skip to content

Article

InteractAgent: A Memory-Augmented Reflection Agent for Long-Horizon Human-Scene Interaction Animation

arXiv cs.RO

The paper proposes InteractAgent, a multimodal large language model agent system for long-horizon human-scene interaction that completes planning, execution, observation, and reflection in a closed loop, with a single MLLM serving as both planner and evaluator and a frozen MotionLLM as the executor.

Part of the event: InteractAgent: A Human-Scene Interaction System with Memory Reflection

This page provides a summary and source link only.