AI RESEARCH
Test-Time Deep Thinking to Explore Implicit Rules
arXiv CS.AI
•
ArXi:2605.24828v1 Announce Type: new With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed directly and must be inferred through interaction. This causes agents to fall into repetitive trial-and-error loops, ultimately leading to task failure.