VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks.
Jing Yu KohRobert LoLawrence JangVikram DuvvurMing Chong LimPo-Yu HuangGraham NeubigShuyan ZhouRuss SalakhutdinovDaniel FriedPublished in: ACL (1) (2024)
Keyphrases
- multi agent systems
- web applications
- visual tasks
- website
- cooperative
- multi agent
- web mining
- multiagent systems
- web documents
- software agents
- multi modal
- information sources
- autonomous agents
- information gathering
- low level
- multiple agents
- coalition formation
- dynamic environments
- mobile agents
- working environment
- resource allocation
- semantic web
- web images
- crowd simulation
- web resources
- end users
- real life
- multimedia
- linked data
- web pages
- decision making
- cross modal
- real world
- cognitive effort
- multimodal information
- multi agent environments
- interacting agents
- sharing information
- agent model
- visual features
- user generated content
- link analysis