Skip to content
Preprint

OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping

Jul 2026 · 0 citations · 26 references
Computer Science

TL;DR

OS-Pruner is a lightweight plug-in framework that formulates chain-of-thought pruning as an optimal stopping problem that achieves 20-60\% reduction in generation length with minimal accuracy sacrifice on diverse reasoning benchmarks and base models.

Abstract

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, these models often exhibit"computational overthinking,"generating redundant reasoning steps that increase latency and cost without improving accuracy. Recent studies suggest that CoT trajectories can be significantly pruned, yet existing methods often rely on forcing a static thinking budget, heuristic filtering, sub-optimal early exit via classification, or expensive re-training. In this paper, we introduce OS-Pruner, a lightweight plug-in framework that formulates chain-of-thought pruning as an optimal stopping problem. Given a reasoning prefix, OS-Pruner learns whether further reasoning is worth its token cost by optimizing an explicit utility that trades off final-answer accuracy against generated length. Our novel formulation enables the model to dynamically assess the sufficient point of termination for a reasoning chain. OS-Pruner is designed to be lightweight during both training and inference, and to provide users with fine-grained control over the reasoning-effort vs. accuracy trade-off. On diverse reasoning benchmarks and base models, OS-Pruner achieves 20-60\% reduction in generation length with minimal accuracy sacrifice.

View source

Similar papers

Preprint Aug 2026

ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning

This work proposes ChainPrune, a novel reasoning path semantic structural optimization method to efficiently and controllably synthesize self-generated high-quality training data and incorporates a DPO-based preference learning method combined with supervised loss, effectively mitigating false reward suppression.

Weihang Pan, Zhengxu Yu, Yuxiang Zhang et al. · 1 citation
2025

Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps

This work presents a theoretical framework that reveals how reasoning steps can amplify error through three failure modes: incorrect sub-task decomposition, incorrect sub-task solving, and incorrect final answer summarization, and introduces structured interventions that adapt CoT generation according to the identified failure types.

Haibo Jin, Peiyan Zhang, Man Luo et al. · 1 citation
Conference Open access 2026

CLARO: Controlled Attribute-Driven Reasoning Optimization for Efficient Chain-of-Thought

Overall, the findings establish that optimizing the thought process structure refines reasoning efficacy, with computational efficiency emerging as a derivative benefit of a clearer thought process.

Oded Schlesinger, Young Kyung Kim, J. Matias Di Martino et al. · 0 citations

Sprint or Delve: A Distribution-Aware Approach to Efficient Reasoning

The Powered Length Penalty (PLP) is proposed, an adaptive regularizer that penalizes redundancy in short sequences while gradually reducing penalties for longer sequences, preserving deep reasoning.

Zehui Ling, Deshu Chen, Hongwei Zhang et al. · 0 citations
Preprint Jul 2026

Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming

Reason Popper-ly, a neurosymbolic framework that uses inductive logic programming (ILP) to learn relation composition rules from reasoning traces and deploys them as an online verifier for step-level correction, consistently improves terminal accuracy over standard CoT.

Zirong Chen, Meiyi Ma · 0 citations
Conference Jul 2026

AdaptiReason: Adaptive Chain-of-Thought Compression for Efficient Large Language Model Inference

Large Language Models (LLMs) trained using Chain-of-Thought (CoT) supervision have achieved state-of-the-art performance on complex reasoning tasks. However, the generation of long reasoning chains introduces substantial computational overhead during inference, limiting their deployment in low-latency and resource-constrained environments. This paper proposes AdaptiReason, a novel framework that dynamically compresses intermediate reasoning steps based on task difficulty and model confidence without requiring retraining of the underlying base model. AdaptiReason employs a lightweight difficulty estimator to determine the appropriate reasoning depth for each input, followed by a learned token-pruning policy that eliminates redundant or low-information reasoning steps. Experimental evaluation on the MATH, GSM8K, and ARC-Challenge benchmarks demonstrates that AdaptiReason reduces the average number of generated tokens by 3.7× while preserving 98.2% of the baseline reasoning accuracy. Furthermore, the proposed framework is model-agnostic and can be seamlessly integrated with instruction-tuned LLMs without requiring access to model parameters, relying solely on output logits for adaptive reasoning compression. The results demonstrate that AdaptiReason significantly improves inference efficiency while maintaining high reasoning performance, making it suitable for real-time and resource-constrained LLM applications.

V. A, Mithaguru, Amrita Kundu et al. · 0 citations