analiza aiqbench
This research introduces HexLogicAgent, a framework that addresses LLM reasoning failures by explicitly organizing implicit semantic relations using semiotic logical hexagon theory. The study demonstrates that incomplete semantic representations are the primary cause of logical errors in large models and shows how modeling complete structures of opposition improves reliability on complex benchmarks. By shifting focus from mere deductive inference to foundational semantic organization, this work offers a novel approach to enhancing LLM robustness without relying solely on external solvers or self-verification loops.
Semiotic logical hexagon theory for LLM logical reasoning
arXiv:2607.21933v1 Announce Type: new Abstract: Large language models (LLMs) have become powerful tools for language understanding and logical reasoning. However, they still make mistakes when a problem requires both understanding meaning and following logic. A key reason is that natural-language statements often carry implicit semantic relations before any formal reasoning begins. If these hidden meanings are not properly organized, the model may reach incorrect conclusions even when the subsequent reasoning process appears logically valid. Existing methods improve reasoning through decomposition, symbolic translation, external solvers, or self-verification, but pay comparatively less attention to the semantic structure on which reasoning depends. In this paper, we further investigate how semantic organization influences logical reasoning in LLMs. To this end, we propose HexLogicAgent, a framework that first organizes the meaning of natural-language statements and then guides logical reasoning through structured verification. In our investigation, we also make two observations. First, incomplete semantic representations, rather than deductive inference itself, are a major source of logical reasoning failures in LLMs. Second, explicitly modeling the complete structure of semantic opposition substantially delays the degradation of reasoning performance as logical complexity increases. Experiments on challenging logical reasoning benchmarks demonstrate that HexLogicAgent consistently improves reasoning reliability across multiple LLMs. The core idea is supported by a logical hexagon theory, which explains why a complete structure of opposing meanings is necessary for reliable reasoning.
Abstract:Large language models (LLMs) have become powerful tools for language understanding and logical reasoning. However, they still make mistakes when a problem requires both understanding meaning and following logic. A key reason is that natural-language statements often carry implicit semantic relations before any formal reasoning begins. If these hidden meanings are not properly organized, the model may reach incorrect conclusions even when the subsequent reasoning process appears logically valid. Existing methods improve reasoning through decomposition, symbolic translation, external solvers, or self-verification, but pay comparatively less attention to the semantic structure on which reasoning depends. In this paper, we further investigate how semantic organization influences logical reasoning in LLMs. To this end, we propose HexLogicAgent, a framework that first organizes the meaning of natural-language statements and then guides logical reasoning through structured verification. In our investigation, we also make two observations. First, incomplete semantic representations, rather than deductive inference itself, are a major source of logical reasoning failures in LLMs. Second, explicitly modeling the complete structure of semantic opposition substantially delays the degradation of reasoning performance as logical complexity increases. Experiments on challenging logical reasoning benchmarks demonstrate that HexLogicAgent consistently improves reasoning reliability across multiple LLMs. The core idea is supported by a logical hexagon theory, which explains why a complete structure of opposing meanings is necessary for reliable reasoning.
Artificial Intelligence (cs.AI)
arXiv:2607.21933 [cs.AI]
(or arXiv:2607.21933v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.21933 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 313 cuvinte
Subiecte conexe
The Next Swan: Frank Ramsey, Variable Hypotheticals, and the Bet on Induction
LessWrong · 8 iun. 2026
Quantum agents can reason consistently, new framework shows
Quantum Zeitgeist · 10 sept. 2026
The Entangled Dimensions of Decision Theory
LessWrong · 30 iul. 2026
Pulling hedonic utilitarianism out of ethical emotivism
LessWrong · 13 iun. 2026