#llm agent

A symbolic simulation environment compiled from real kitchen videos for evaluating large-model agents on long-horizon embodied tasks.

A retrieval-control framework for legal consultation based on element coverage, evidence coverage, and marginal gain.

A video-driven symbolic simulator and belief-state planning benchmark built from HD-EPIC egocentric cooking videos.

A legal QA and agent system integrating Graph-RAG, reinforcement learning, harness engineering, and multi-agent collaboration.

An LLM-agent direction for material design, formulation-performance prediction, and scientific workflow support.