CREW-WILDFIRE Benchmark

What is CREW-WILDFIRE?

CREW-WILDFIRE is a benchmark designed to evaluate large language model-based multi-agent systems’ collaboration capabilities in complex, dynamic tasks…

Released

2025-07-07

Evaluates

智能体, Agent, 任务执行, Task Execution, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

CREW-WILDFIRE paper and code

• Paper https://arxiv.org/abs/2507.05178
• Code https://github.com/generalroboticslab/CREW

Which sources cite CREW-WILDFIRE?

• CREW-WILDFIRE

Related 智能体, Agent, 任务执行, Task Execution, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard