Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use

By Song-Lin Lv · Paper · cs.AI

While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics. To address this generalization gap, we formalize OpenAgent (Tool-

AI Agents · Model Launch · Cs.ai

View original

HomeResourceLoading…