EmbodiedAgentInterface Benchmark

What is EmbodiedAgentInterface?

Embodied Agent Interface supports the formalization of various types of tasks and input-output specifications of LLM-based modules, offering a comprehensive…

Released

2024-06-24

Evaluates

推理, Reasoning, Embodied Decision Making, NeurIPS 2024, 物理智能, Embodied AI, 逻辑推理, 具身交互, Embodied Interaction, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/EmbodiedAgentInterface

EmbodiedAgentInterface paper, code and dataset

• Paper https://arxiv.org/abs/2410.07166
• Code https://github.com/embodied-agent-interface/embodied-agent-interface
• Dataset https://huggingface.co/datasets/Inevitablevalor/EmbodiedAgentInterface

Which sources cite EmbodiedAgentInterface?

• EmbodiedAgentInterface

Related 推理, Reasoning, Embodied Decision Making, NeurIPS 2024, 物理智能, Embodied AI, 逻辑推理, 具身交互, Embodied Interaction, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench