AI RESEARCH
SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents
arXiv CS.CV
•
ArXi:2605.18636v1 Announce Type: new Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Existing approaches often trade off costly per-step reasoning against reactive execution that can drift, repeat failures, and recover poorly. Our key idea is to reuse strategic reasoning across locally stable segments and reinvoke it at event boundaries. We present SPIKE, an adaptive dual controller framework for cost-efficient long-horizon game control.