Research2026-05-14
interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification
Source: Arxiv CS.AI
arXiv:2602.11202v3 Announce Type: replace-cross Abstract: 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...
arxivpapersreasoning