A State-Transition Framework for Efficient LLM Reasoning

2026-02-01

AI Summary

This work proposes an efficient reasoning framework based on state transitions to address the high computational and memory costs of chain-of-thought (CoT) reasoning in large language models, which hinder practical deployment and conflict with test-time scaling. The approach models reasoning as a state evolution process and incorporates a linear attention mechanism to reduce attention complexity, enabling each step to leverage prior reasoning states without explicitly accessing all historical tokens. Additionally, a state-based reasoning strategy is introduced to mitigate overthinking caused by noisy intermediate steps. Experimental results across multiple datasets and model scales demonstrate that the method significantly improves both reasoning efficiency and performance.

Technology Category

• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

While Long Chain-of-Thought (CoT) reasoning significantly improves Large Language Models (LLMs) performance on complex reasoning tasks, the substantial computational and memory costs of generating long CoT sequences limit their efficiency and practicality. Existing studies usually enhance the reasoning efficiency of LLMs by compressing CoT sequences. However, this approach conflicts with test-time scaling, limiting the reasoning capacity of LLMs. In this paper, we propose an efficient reasoning framework that models the reasoning process of LLMs as a state-transition process. Specifically, we first apply a linear attention mechanism to estimate the LLM's reasoning state, which records the historical reasoning information from previous reasoning steps. Then, based on the query prompt and the reasoning state, the LLM can efficiently perform the current reasoning step and update the state. With the linear attention, each token in the current reasoning step can directly retrieve relevant historical reasoning information from the reasoning state, without explicitly attending to tokens in previous reasoning steps. In this way, the computational complexity of attention is reduced from quadratic to linear, significantly improving the reasoning efficiency of LLMs. In addition, we propose a state-based reasoning strategy to mitigate the over-thinking issue caused by noisy reasoning steps. Extensive experiments across multiple datasets and model sizes demonstrate that our framework not only improves the reasoning efficiency of LLMs but also enhances their reasoning performance.

Problem

• Large Language Models
• Chain-of-Thought Reasoning
• Reasoning Efficiency
• Computational Cost
• Test-time Scaling

Innovation

• state-transition
• linear attention
• efficient reasoning
• large language models
• reasoning state