LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization

• URL: http://arxiv.org/abs/2507.15758v2
• Date: Thu, 14 Aug 2025 08:13:36 GMT
• Title: LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
• Authors: Xingyu Wu, Yuchen Yan, Shangke Lyu, Linjuan Wu, Yiwen Qiu, Yongliang Shen, Weiming Lu, Jian Shao, Jun Xiao, Yueting Zhuang,
• Abstract summary: Length-Adaptive Policy Optimization transforms reasoning length control from an external constraint into an intrinsic model capability.<n>LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process.<n> Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9% while improving accuracy by 2.3%.
• Score: 48.91511514636768
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for simple problems. We present Length-Adaptive Policy Optimization (LAPO), a novel framework that transforms reasoning length control from an external constraint into an intrinsic model capability. Unlike existing approaches that impose rigid limits or rely on post-hoc interventions, LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process. In the first stage, models learn natural reasoning patterns by discovering the statistical distribution of successful solution lengths. The second stage leverages these patterns as meta-cognitive guidance, embedding them directly within the model's reasoning context to ensure inference-time flexibility. Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9% while improving accuracy by 2.3%. Our analysis reveals that models trained with LAPO develop emergent abilities to allocate computational resources based on problem complexity, achieving efficient reasoning without sacrificing quality.

Related papers

• Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning [49.290631188365786]
  Scaf-GRPO is a training framework that intervenes when a model's independent learning has plateaued.<n>It boosts the pass@1 score of the Qwen2.5-Math-7B model by a relative 44.3% over a vanilla GRPO baseline.<n>This result demonstrates our framework provides a robust and effective methodology for unlocking a model's ability to solve problems previously beyond its reach.
  arXiv  Detail & Related papers  (2025-10-22T17:41:30Z)
• Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints [6.506004562943421]
  Test-time compute scaling has demonstrated the ability to improve the performance of reasoning language models by generating longer chain-of-thought sequences.<n>This increase in performance comes with a significant increase in computational cost.<n>We investigate two compute constraint strategies to reduce the compute demand of reasoning models and study their impact on their safety performance.
  arXiv  Detail & Related papers  (2025-09-22T20:09:37Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• HEFT: A Coarse-to-Fine Hierarchy for Enhancing the Efficiency and Accuracy of Language Model Reasoning [0.0]
  HEFT is a novel hierarchical adaptation strategy that composes two distinct PEFT methods in a coarse-to-fine manner.<n>A model fine-tuned for only three epochs with our HEFT strategy achieves an accuracy of 85.17%, exceeding the performance of models trained for 20 epochs.
  arXiv  Detail & Related papers  (2025-09-11T19:06:46Z)
• TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making [75.29820290660065]
  This paper proposes Thought-Centric Preference Optimization ( TCPO) for effective embodied decision-making.<n>It emphasizes the alignment of the model's intermediate reasoning process, mitigating the problem of model degradation.<n>Experiments in the ALFWorld environment demonstrate an average success rate of 26.67%, achieving a 6% improvement over RL4VLM.
  arXiv  Detail & Related papers  (2025-09-10T11:16:21Z)
• Hierarchical Budget Policy Optimization for Adaptive Reasoning [49.621779447691665]
  We present Hierarchical Budget Policy Optimization (HBPO), a reinforcement learning framework that enables models to learn problem-specific reasoning depths without sacrificing capability.<n>HBPO addresses the challenge of exploration space collapse in efficiency-oriented training, where penalties on long output length systematically bias models away from necessary long reasoning paths.<n>Extensive experiments demonstrate that HBPO reduces average token usage by up to 60.6% while improving accuracy by 3.14% across four reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-07-21T17:52:34Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search [15.387256204743407]
  Large language models (LLMs) demand considerable computational, energy, and financial resources during both training and deployment.<n>Inference costs now represent a significant and growing component of the overall resource burden.<n>We introduce directed skill search (DS3), a general framework that represents inference as expressive over a learned skill graph.
  arXiv  Detail & Related papers  (2025-06-10T14:47:48Z)
• Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning [17.421901873720156]
  This paper proposes a novel RL framework called textbfVision-EKIPL.<n>It introduces high-quality actions generated by external auxiliary models during the RL training process to guide the optimization of the policy model.<n>It achieves up to a 5% performance improvement on the Reason-RFT-CoT Benchmark compared to the state-of-the-art (SOTA)
  arXiv  Detail & Related papers  (2025-06-07T16:37:46Z)
• Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration [15.711365331854614]
  We introduce Dynamic Adaptation of Reasoning Trajectories (DART), a novel data adaptation framework.<n>Instead of uniformly imitating expert steps, DART employs a selective imitation strategy guided by step-wise adaptability estimation.<n>We validate DART across multiple reasoning benchmarks and model scales, demonstrating that it significantly improves generalization and data efficiency.
  arXiv  Detail & Related papers  (2025-05-27T04:08:11Z)
• Hybrid Latent Reasoning via Reinforcement Learning [51.06635386903026]
  We explore latent reasoning by leveraging the capabilities of large language models (LLMs) via reinforcement learning (RL)<n>We introduce hybrid reasoning policy optimization (HRPO), an RL-based hybrid latent reasoning approach that integrates prior hidden states into sampled tokens with a learnable gating mechanism.<n>HRPO-trained LLMs remain interpretable and exhibit intriguing behaviors like cross-lingual patterns and shorter completion lengths.
  arXiv  Detail & Related papers  (2025-05-24T01:26:16Z)
• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees [3.4289478404209826]
  Large Language Models excel in generative tasks but exhibit inefficiencies in structured text selection.<n>We propose a Learning-to-Defer framework that allocates queries to specialized experts, ensuring high-confidence predictions.
  arXiv  Detail & Related papers  (2024-10-21T08:21:00Z)
• The Role of Deductive and Inductive Reasoning in Large Language Models [35.43513487137371]
  We propose the Deductive and InDuctive(DID) method to enhance Large Language Models (LLMs) reasoning.<n>DID implements a dual-metric complexity evaluation system that combines Littlestone dimension and information entropy.<n>Our results demonstrate significant improvements in reasoning quality and solution accuracy.
  arXiv  Detail & Related papers  (2024-10-03T18:30:47Z)
• Learning Constrained Optimization with Deep Augmented Lagrangian Methods [54.22290715244502]
  A machine learning (ML) model is trained to emulate a constrained optimization solver. This paper proposes an alternative approach, in which the ML model is trained to predict dual solution estimates directly. It enables an end-to-end training scheme is which the dual objective is as a loss function, and solution estimates toward primal feasibility, emulating a Dual Ascent method.
  arXiv  Detail & Related papers  (2024-03-06T04:43:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.