EmbodiedBench

'EmbodiedBench' is a benchmark dataset used to evaluate the reasoning capabilities of embodied agents in performing long-horizon manipulation tasks in complex real-world environments.

Papers using EmbodiedBench (4)

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents2025 · 1 citesMemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents2026RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning2025RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems2025