AI RESEARCH

interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification

arXiv CS.AI

ArXi:2602.11202v3 Announce Type: replace-cross Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctness. Existing approaches either verify only the final answer, which misses early errors, or rely on branch-and-verify strategies that explore multiple trajectories. We