AI RESEARCH
Can LLM Agents Sustain Long-Horizon Organizational Dynamics?
arXiv CS.AI
•
ArXi:2606.01199v1 Announce Type: new Large language agents are increasingly used for social simulation, yet it remains unclear whether they can sustain coherent behavior in structured organizations, where goals must propagate through hierarchy, tasks depend on prior execution, and artifacts accumulate over long horizons. We formulate long-horizon organizational simulation as a memory-centered coordination problem and