2 papers
cs.AI2026
Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought?
Jiashu He, Jinxuan Fan, Xiao Xiao +2
Reasoning models generate long chains of thought before they answer, yet it is debated whether the content of these chains does real computational work or is largely decorative. We…
cs.AI2026
Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents
Zhaofeng Li, Xuan Zhang, Xiaokui Xiao +1
Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty. Existing proactive approaches often speciali…