Structured Abductive-Deductive-Inductive Reasoning for LLMs via Algebraic Invariants

arXiv:2604.15727v1 Announce Type: new Abstract: Large language models exhibit systematic limitations in structured logical reasoning: they conflate hypothesis generation with verification, cannot distinguish conjecture from validated knowledge, and allow weak reasoning steps to propagate unchecked through inference chains. We present a symbolic reasoning scaffold that operationalizes Peirce's tripartite inference -- abduction, deduction, and induction -- as an explicit protocol for LLM-assisted reasoning. The framework enforces logical consistency through five algebraic invariants (the Gamma Quintet), the strongest of which -- the Weakest Link bound -- ensures that no conclusion in a reasoning chain can exceed the reliability of its least-supported premise. This principle, independently grounded as weakest link resolution in possibilistic logic and empirically validated for chain-of-thought reasoning, prevents logical inconsistencies from accumulating across multi-step inference. We verify all invariants through a property-based testing suite of 100 properties and 16 fuzz tests over 10^5+ generated cases, providing a verified reference implementation of the invariants suitable as a foundation for future reasoning benchmarks.

Related

• KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning
• A Survey of Inductive Reasoning for Large Language Models
• ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning
• Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting

Source: arXiv cs.AI | 2026-04-20