Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning

arXiv:2601.02902v2 Announce Type: replace-cross Abstract: Symbolic logical reasoning is a critical yet underexplored capability of large language models (LLMs), providing reliable and verifiable decision-making in high-stakes domains such as mathematical reasoning and legal judgment. In this study, we present a systematic analysis of logical reasoning under controlled increases in logical complexity, and reveal a previously unrecognized phenomenon, which we term Logical Phase Transitions: rather than degrading smoothly, logical reasoning performance remains stable within a regime but collapses abruptly beyond a critical logical depth, mirroring physical phase transitions such as water freezing beyond a critical temperature threshold. Building on this insight, we propose Neuro-Symbolic Curriculum Tuning, a principled framework that adaptively aligns natural language with logical symbols to establish a shared representation, and reshapes training dynamics around phase-transition boundaries to progressively strengthen reasoning at increasing logical depths. Experiments on five benchmarks show that our approach effectively mitigates logical reasoning collapse at high complexity, yielding average accuracy gains of +1.26 in naive prompting and +3.95 in CoT, while improving generalization to unseen logical compositions. Code and data are available at https://github.com/AI4SS/Logical-Phase-Transitions.

Related

• Mathematical Reasoning Enhanced LLM for Formula Derivation: A Case Study on Fiber NLI Modellin
• A Decomposition Perspective to Long-context Reasoning for LLMs
• Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs
• Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs

Source: arXiv cs.CL | 2026-04-16