From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models

TL;DR

This paper redefines reasoning in large language models as an adaptive process, emphasizing input-dependent effort allocation, and provides a formal framework and taxonomy for understanding various adaptive reasoning methods.

Contribution

It formalizes adaptive reasoning in LLMs, connects classical reasoning paradigms with algorithmic implementations, and classifies existing methods into training-based and training-free approaches.

Findings

Formalization of deductive, inductive, and abductive reasoning in LLMs.

A control-augmented policy optimization framework for adaptive reasoning.

A taxonomy organizing methods into training-based and training-free categories.

Abstract

Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence. While prior surveys focus on efficiency by examining how to shorten reasoning chains or reduce computation, this view overlooks a fundamental challenge: current LLMs apply uniform reasoning strategies regardless of task complexity, generating long traces for trivial problems while failing to extend reasoning for difficult tasks. This survey reframes reasoning through the lens of {adaptivity}: the capability to allocate reasoning effort based on input characteristics such as difficulty and uncertainty. We make three contributions. First, we formalize deductive, inductive, and abductive reasoning within the LLM context, connecting these classical cognitive paradigms with their algorithmic realizations. Second, we formalize adaptive reasoning as a control-augmented policy optimization problem balancing task performance with computational cost, distinguishing learned policies from inference-time control mechanisms. Third, we propose a systematic taxonomy organizing existing methods into training-based approaches that internalize adaptivity through reinforcement learning, supervised fine-tuning, and learned controllers, and training-free approaches that achieve adaptivity through prompt conditioning, feedback-driven halting, and modular composition. This framework clarifies how different mechanisms realize adaptive reasoning in practice and enables systematic comparison across diverse strategies. We conclude by identifying open challenges in self-evaluation, meta-reasoning, and human-aligned reasoning control.