Open access
Jul 2026
Empirical Analysis of Chain-of-Thought and Solver-Augmented Large Language Models for Deductive Reasoning
These results indicate that while CoT-augmented LLMs achieve strong performance on deductive reasoning tasks up to five hops, solver augmentation remains valuable for deeper multihop deduction and for applications requiring robust and verifiable reasoning.
Ya Wang, Raja Havish Seggoju, A. Paschke
· Neurosymbolic Artificial Int... · 0 citations