AI RESEARCH
Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents
arXiv CS.LG
•
ArXi:2603.17683v1 Announce Type: cross Large language model (LLM) agents deployed in unknown environments must learn task structure at test time, but current approaches require thousands of interactions to form useful hypotheses. We present Sensi, an LLM agent architecture for the ARC-AGI-3 game-playing challenge that