VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks.
Jing Yu KohRobert LoLawrence JangVikram DuvvurMing Chong LimPo-Yu HuangGraham NeubigShuyan ZhouRuslan SalakhutdinovDaniel FriedPublished in: CoRR (2024)
Keyphrases
- multi agent
- multi agent systems
- visual tasks
- autonomous agents
- semantic web
- web applications
- multiple agents
- cooperative
- information gathering
- low level
- crowd simulation
- information sources
- real life
- website
- multimodal information
- multiagent systems
- visual information
- multi modal
- visual features
- web pages
- web resources
- agent systems
- web images
- agent technology
- software agents
- metadata
- human users
- artificial agents
- decision making
- web intelligence
- mobile agents
- intelligent agents
- distributed systems
- web data
- web technologies
- user generated content
- linked data
- web mining
- resource allocation
- web documents
- working environment
- coordination mechanism
- end users