Agent-Guided Process Verification for Mathematical Self-Correction
Large language models have made substantial progress in mathematical reasoning, yet in complex multi-step reasoning, an error at any step may propagate along an incorrect path, and the resulting solution may omit necessary branches.
By Rui Zou, Mengqi Wei, Xin Zhao, Ji-Rong WenarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Nov 17, 2026.
Comments
Sign in to join the discussion.