Frontier AI & Multi-Agent Systems

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

OpenAgent formalizes the open-world generalization gap in tool-use LLM agents across four non-stationary dimensions: queries, tool schemas, feedback dynamics, and task domains. Diagnostic experiments reveal that SFT agents suffer from brittle symbolic anchoring and open-loop inertia, while RL agents display …