SOURCE-LINKED INTELLIGENCE

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Chain-of-Thought (CoT) improves the reasoning ability of Large Language Models (LLMs) but incurs substantial computation and context costs. Existing methods either lose intermediate information through hard pruning or lack a principled criterion for continuous compression. We present A*-Thought-V2, a geometric dynamics of LLM guided framework that models CoT as a hidden-state trajectory and replaces hard deletion with an explicit-implicit interleaved latent architecture. After projecting question, step, and solution representations into a 3D PCA space, it measures alignment between each local

Read original source ↗ Open in workspace

recordType

paper

region

Global