Metraipolis › archive › dc_b4bb7c4acd87
BiVerify: Closing the Loop Between Backward and Forward Verification for Mathematical Self-Correction — arXiv:2611.11368
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11368
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:21.663Z
- SHA-256 of the archived text
06bd952fd229ca43267fc77c20917d5ed6bda3118f2c3d458d8a37a714039b85- Stable URL of this page
https://metraipolis.com/documento/dc_b4bb7c4acd87
How to cite
BiVerify: Closing the Loop Between Backward and Forward Verification for Mathematical Self-Correction — arXiv:2611.11368 — arXiv (en), https://arxiv.org/abs/2611.11368 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b4bb7c4acd87 (Metraipolis archive dc_b4bb7c4acd87, sha256 06bd952fd229ca43267fc77c20917d5ed6bda3118f2c3d458d8a37a714039b85)
BibTeX
@misc{dcb4bb7c4acd87,
title = {BiVerify: Closing the Loop Between Backward and Forward Verification for Mathematical Self-Correction — arXiv:2611.11368},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11368},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b4bb7c4acd87; sha256 06bd952fd229ca43267fc77c20917d5ed6bda3118f2c3d458d8a37a714039b85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11368. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) have made substantial progress in mathematical reasoning but still produce incorrect solutions to complex problems, indicating the need for more reliable self-correction mechanisms. Mathematical self-correction typically identifies errors through verification, which can proceed backward or forward. The two directions provide complementary verification capabilities. Backward verification checks a candidate answer against the original constraints, bypassing complex intermediate reasoning, but cannot ensure correct reasoning or objective completeness. Forward verification follows the problem conditions and current solution, enabling it to locate reasoning errors and assess objective completeness, but may overlook key constraints in complex solution chains. We propose BiVerify, a dynamically scheduled framework for bidirectional mathematical verification. BiVerify begins with backward verification to screen the answer against the original constraints, followed by forward verification of the reasoning process; subsequent direction switching, state resetting, and re-verification are governed by verification outcomes. Upon failure, the system revises the candidate or verification flow until the same candidate passes both directions. We also introduce shared mathematical tools that separate logical reasoning from precise computation. We systematically evaluate BiVerify on five challenging mathematical reasoning benchmarks using multiple mainstream DeepSeek, GPT, and Gemini models. BiVerify exceeds the strongest representative public baseline evaluated in this work by 13.5 percentage points in average accuracy, with the margin reaching 31.2 percentage points on GPT. Further analysis shows that BiVerify's overall performance exceeds that of either verification direction alone. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.11368 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:37.512Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).