Jul 2026
Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming
Reason Popper-ly, a neurosymbolic framework that uses inductive logic programming (ILP) to learn relation composition rules from reasoning traces and deploys them as an online verifier for step-level correction, consistently improves terminal accuracy over standard CoT.
Zi-Rong Chen, Mei-Yi Ma
· arXiv.org · 0 citations