{"slug": "when-do-llms-reason-a-dynamical-systems-view-via-entropy-phase-transitions", "title": "When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions", "summary": "Researchers have found that chain-of-thought reasoning in large language models is only beneficial when early-stage entropy dynamics show consistent reduction, according to a new study on arXiv. The team introduced EDRM, a lightweight routing framework that uses early decoding entropy to selectively apply reasoning, achieving up to 55% token reduction and 4.7% accuracy gains across 15 benchmarks. The findings challenge the default use of CoT reasoning, suggesting it should be invoked adaptively rather than universally.", "body_md": "arXiv:2605.22873v1 Announce Type: new\nAbstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial? Empirical evidence reveals a striking paradox: CoT often provides marginal or even negative gains on factual and open-ended tasks while multiplying token consumption. In this work, we show that LLM reasoning is not a static property of tasks or models, but a \\emph{dynamic decoding state} that emerges during generation. Through systematic analysis, we find early-stage entropy dynamics provide a reliable signal of this state: tasks benefiting from CoT exhibit consistent entropy reduction, while others display unstable or increasing patterns. This behavior can be interpreted as a phase-transition-like shift from a high-entropy exploratory regime to a low-entropy structured reasoning regime. Based on these insights, we propose \\textbf{EDRM} (Entropy Dynamics-based Reasoning Manifold), a lightweight and training-free routing framework that leverages early decoding entropy to adaptively select inference strategies. EDRM embeds entropy trajectories into a compact and interpretable manifold representation, enabling both zero-shot deployment and fine-grained instance-level adaptation. Across 15 benchmarks and 4 LLMs of varying scales and architectures, EDRM consistently outperforms static baselines. At the dataset level, EDRM achieves \\textbf{41--55\\%} token reduction while improving accuracy with as few as 50 calibration samples. At the instance level, it further improves accuracy by up to \\textbf{4.7\\%} while maintaining \\textbf{27--45\\%} token savings. These results suggest that reasoning should be invoked selectively rather than by default, and demonstrate the effectiveness of entropy-driven decoding control for efficient and adaptive LLM inference.", "url": "https://wpnews.pro/news/when-do-llms-reason-a-dynamical-systems-view-via-entropy-phase-transitions", "canonical_source": "https://arxiv.org/abs/2605.22873", "published_at": "2026-05-25 04:00:00+00:00", "updated_at": "2026-05-25 15:13:25.098991+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "machine-learning", "neural-networks", "ai-research"], "entities": ["EDRM", "CoT"], "alternates": {"html": "https://wpnews.pro/news/when-do-llms-reason-a-dynamical-systems-view-via-entropy-phase-transitions", "markdown": "https://wpnews.pro/news/when-do-llms-reason-a-dynamical-systems-view-via-entropy-phase-transitions.md", "text": "https://wpnews.pro/news/when-do-llms-reason-a-dynamical-systems-view-via-entropy-phase-transitions.txt", "jsonld": "https://wpnews.pro/news/when-do-llms-reason-a-dynamical-systems-view-via-entropy-phase-transitions.jsonld"}}