Metraipolis › archive › dc_43f34e2ef1b0
Rewarding Novel Deductions: Solver-guided Process Supervision for Logical Reasoning — arXiv:2609.34660
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34660
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:53:29.102Z
- SHA-256 of the archived text
1e345f71dc39784c2241e89b4ddb44aa5a7f83edd1d46379ac0f136e0206bf27- Stable URL of this page
https://metraipolis.com/documento/dc_43f34e2ef1b0
How to cite
Rewarding Novel Deductions: Solver-guided Process Supervision for Logical Reasoning — arXiv:2609.34660 — arXiv (en), https://arxiv.org/abs/2609.34660 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43f34e2ef1b0 (Metraipolis archive dc_43f34e2ef1b0, sha256 1e345f71dc39784c2241e89b4ddb44aa5a7f83edd1d46379ac0f136e0206bf27)
BibTeX
@misc{dc43f34e2ef1b0,
title = {Rewarding Novel Deductions: Solver-guided Process Supervision for Logical Reasoning — arXiv:2609.34660},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34660},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43f34e2ef1b0; sha256 1e345f71dc39784c2241e89b4ddb44aa5a7f83edd1d46379ac0f136e0206bf27},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34660. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Logical reasoning remains a major challenge for large language models (LLMs), particularly on structured problems that require precise constraint tracking, consistency preservation, and multi-step deduction. This challenge is especially acute for small-scale LLMs, which are more prone to producing inconsistent, redundant, or brittle reasoning trajectories. Existing approaches for improving logical reasoning largely optimize for final-answer correctness, providing only weak supervision over the intermediate reasoning process. In this work, we propose SPRING: (Solver-guided Process Rewards for Novel LogIcal ReasoNing Step Generation). SPRING uses SMT solver as a training-time verifier of intermediate reasoning steps to provide process-level supervision. It introduces the notion of a novel reasoning step, namely, a step that is logically valid, consistent with the evolving reasoning state, and not already implied by previously accepted non-contradictory deductions. Based on this solver-based assessment, it designs process rewards that encourage novel inferential progress while penalizing contradictory and uninformative reasoning steps. Evaluation across three logical reasoning benchmarks, ZebraLogic, AR-LSAT, and Knights and Knaves, and four LLMs shows that SPRING consistently outperforms base LLMs, outcome-only reward baselines, and Logic-LM. On ZebraLogic, SPRING improves puzzle accuracy by up to 49.71 and 15.43 points over the base LLM and strongest outcome-only baseline, respectively. On AR-LSAT, it improves overall accuracy by up to 64.93 and 12.14 points, respectively. On Knights and Knaves, SPRING achieves up to 93.14 puzzle accuracy and 96.05 person accuracy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.34660 — 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 2026-10-07T21:27:08.628Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).