🏢 University of Maryland
GUI Agents: A Survey
·360 words·2 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Multimodal Learning
Human-AI Interaction
🏢 University of Maryland
A comprehensive survey of GUI agents, categorizing benchmarks, architectures, training methods, and open challenges, providing a unified framework for researchers.
DynaSaur: Large Language Agents Beyond Predefined Actions
·2738 words·13 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Large Language Models
🏢 University of Maryland
DynaSaur: a novel LLM agent framework enabling dynamic action creation, surpassing prior methods with greater flexibility and top performance on the GAIA benchmark.