SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs

2025/08/31 by Yanxiao Zhao, Zhao, Yanxiao, Y. Li +16 · 1 citation
Computer Science · #Automated reasoning #Control (management) #Deductive reasoning #Logical consequence #Logical reasoning #Memorization #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Reinforcement learning #Task (project management) #Topic Modeling #cs.AI #cs.LG #cs.LO

paper · pdf · doi:10.18653/v1/2026.acl-long.96

openalex created_date 2025/10/10 · openalex publication_date 2026/01/01 · openalex updated_date 2026/08/05

Abstract

Yanxiao Zhao, Yaqian Li, Zi-Hao Bo, Rinyoichi Takezoe, Haojia Hui, Mo Guang, Renlei, Xiaolin Qin, Kaiwen Long. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Citations

• Are We Done with MMLU?
• Language Models are Few-Shot Learners
• Learning a SAT Solver from Single-Bit Supervision

Cited by

• Solver-Hard Is Not Model-Hard: A Hardness-Controlled Diagnostic for LLM Constraint Reasoning

Related

• SATBench: Benchmarking LLMs' Logical Reasoning via Automated Puzzle Generation from SAT Formulas
• SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
• General-Reasoner: Advancing LLM Reasoning Across All Domains
• SatLM: Satisfiability-Aided Language Models Using Declarative Prompting
• Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks