Web$hell: A Unified Interface for Agentic Web Access
[Sztuczna inteligencja] Autorzy: Sunghwan Kim, Deogyong Kim, Sangam Lee i 2 więcej
Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effective web access is becoming a core capability for agentic problem solving. Existing approaches have advanced agentic web access through different access models, including search-augmented agents, browser-based agents, and, more recently, filesystem-based agents. Nevertheless, as users expect agents to complete long-horizon, end-to-end tasks, they increasingly need to conduct broad information gathering, perform browser actions, and revisit acquired evidence within a single trajectory. Yet our preliminary analyses reveal that existing access models struggle to meet these demands. They primarily support either information gathering or browser interaction, while combining their capabilities can involve substantial costs or performance trade…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja