DCoL-A: Agentic dual chain of thinking helps LLMs pretend logic solvers
Authors:
- Minyu ChenMCMinyu Chen
- Ling-I WuLWLing-I Wu
- Ruibang LiuRLRuibang Liu
- Xi ChangXCXi Chang
- Jianxin XueJXJianxin Xue
- Guoqiang LiGLGuoqiang Li
- 12 March 2026
- journal article
- Published by Elsevier in Journal of Systems Architecture
- Vol. 175
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62532014)
This publication has 10 references indexed in Scilit:
- Large Language Models for Test-Free Fault Localization2024
- Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning2023
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models2023
- Code Execution with Pre-trained Language Models2023
- Analytical Reasoning of Text2022
- ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language2021
- Practical Constraint Solving for Generating System Test DataACM Transactions on Software Engineering and Methodology, 2020
- Verifying multi-threaded software using smt-based context-bounded model checking2011
- Generating hard satisfiability problemsArtificial Intelligence, 1996
- Some pitfalls for experimenters with random SATArtificial Intelligence, 1996