Characterizing How Complex Agentic AI Systems Handle General Tasks: A Trace-Based Simulation Study

Excerpt

arXiv:2606.01725v2 Announce Type: replace Abstract: Agentic AI completes tasks through iterative planning, tool use, and reasoning based on observed outcomes. Despite its popularity, its system-level behavior remains poorly understood, particularly for complex datasets and agent architectures-owing to highly non-deterministic execution, prohibitive evaluation costs, and limited visibility into proprietary models. This paper presents GAIATrace, the first token-level trace dataset of two state-of-