CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents.
Tianqi XuLinyao ChenDai-Jie WuYanjun ChenZecheng ZhangXiang YaoZhiqiang XieYongchao ChenShilong LiuBochen QianPhilip TorrBernard GhanemGuohao LiPublished in: CoRR (2024)
Keyphrases
- language model
- autonomous agents
- agent environment
- multi agent systems
- agent model
- multi agent
- agent receives
- multiagent systems
- multiple agents
- agent interactions
- intelligent agents
- language modeling
- agent behavior
- dynamic environments
- n gram
- document retrieval
- software agents
- virtual agents
- probabilistic model
- robocup soccer
- query expansion
- information retrieval
- speech recognition
- agent architecture
- learning agent
- autonomous entities
- language modelling
- statistical language models
- context sensitive
- retrieval model
- mobile agents
- rational agents
- test collection
- query terms
- ad hoc information retrieval
- smoothing methods
- bayesian networks
- multimedia
- document ranking
- statistical machine translation
- translation model
- vector space model
- mixture model
- query specific
- relevance model