Tag
The author describes a hybrid approach to using LLMs in browser automation tasks, integrating them at build time, repair time, and isolated run time to handle high-volume execution efficiently while minimizing token costs and ensuring reliability.
The paper proposes HybridCUA, a method that combines GUI and CLI interactions for computer-use agents, using a two-stage training framework with supervised fine-tuning and reinforcement learning to improve task accuracy and cross-platform generalizability.
This paper proposes a hybrid knowledge graph generation pipeline that combines top-down grounding in Wikidata with bottom-up agentic synthesis to handle noisy, multilingual HR skill declarations, producing a scalable and self-healing skills taxonomy.