Hierarchical Budget Policy Optimization for Adaptive Reasoning

• URL: http://arxiv.org/abs/2507.15844v3
• Date: Thu, 07 Aug 2025 14:12:39 GMT
• Title: Hierarchical Budget Policy Optimization for Adaptive Reasoning
• Authors: Shangke Lyu, Linjuan Wu, Yuchen Yan, Xingyu Wu, Hao Li, Yongliang Shen, Peisheng Jiang, Weiming Lu, Jun Xiao, Yueting Zhuang,
• Abstract summary: 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 partitions the exploration space into budget-constrained hierarchies (512-2560 tokens), each with differentiated reward structures that preserve both efficiency incentives and reasoning capabilities.<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.
• Score: 49.621779447691665
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large reasoning models achieve remarkable performance through extensive chain-of-thought generation, yet they suffer from a critical inefficiency: applying uniformly extensive reasoning regardless of problem complexity. We present Hierarchical Budget Policy Optimization (HBPO), a reinforcement learning framework that enables models to learn problem-specific reasoning depths without sacrificing capability. Unlike existing approaches that impose rigid constraints or rely on discrete mode selection, HBPO partitions the exploration space into budget-constrained hierarchies (512-2560 tokens), each with differentiated reward structures that preserve both efficiency incentives and reasoning capabilities. This design addresses a fundamental challenge in efficient reasoning training: traditional length penalties systematically bias models away from necessary long reasoning paths, causing exploration space collapse. Through hierarchical sampling and budget-aware rewards, HBPO maintains exploration diversity while teaching models to recognize when extended deliberation is warranted. Extensive experiments demonstrate that HBPO reduces average token usage by up to 60.6% while improving accuracy by 3.14% across four reasoning benchmarks. Most notably, HBPO exhibits emergent adaptive behavior where models automatically adjust reasoning depth based on problem complexity. Our results suggest that reasoning efficiency and capability are not inherently conflicting, and can be simultaneously optimized through appropriately structured hierarchical training that preserves exploration diversity.

Related papers

• LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization [48.91511514636768]
  We present Length-Adaptive Policy Optimization (LAPO), a framework that 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%.
  arXiv  Detail & Related papers  (2025-07-21T16:14:41Z)
• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)
• Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models [68.96619605651155]
  Large reasoning models (LRMs) may drastically increase the output length due to overthinking.<n>We propose a dynamic optimization framework that segments model-generated reasoning paths into distinct thinking patterns.<n>Our method achieves up to a 12% accuracy improvement and reducing token usage from approximately 5,000 to 3,000 tokens.
  arXiv  Detail & Related papers  (2025-05-27T20:59:29Z)
• Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection [7.045509749924679]
  Route-To-Reason (RTR) is a novel unified routing framework that dynamically allocates both LMs and reasoning strategies according to task difficulty under budget constraints.<n>RTR learns compressed representations of both expert models and reasoning strategies, enabling their joint and adaptive selection at inference time.
  arXiv  Detail & Related papers  (2025-05-26T02:53:17Z)
• Plan and Budget: Effective and Efficient Test-Time Scaling on Large Language Model Reasoning [19.258292534503887]
  Plan-and-Budget is a model-agnostic, test-time framework that decomposes complex queries into sub-questions and allocates token budgets based on estimated complexity using adaptive scheduling.<n>Plan-and-Budget improves reasoning efficiency across a range of tasks and models, achieving up to +70% accuracy gains, tangential -39% token reduction, and +187.5% improvement in $E3$.
  arXiv  Detail & Related papers  (2025-05-22T01:56:29Z)
• DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization [55.06360285372418]
  Group Relative Policy Optimization is a reinforcement learning method for large reasoning models (LRMs)<n>In this work, we analyze the GRPO objective under a binary reward setting and reveal an inherent limitation of question-level difficulty bias.<n>We introduce a new Discriminative Constrained Optimization framework for reinforcing LRMs, grounded in the principle of discriminative learning.
  arXiv  Detail & Related papers  (2025-05-18T11:08:32Z)
• Preference Optimization for Combinatorial Optimization Problems [54.87466279363487]
  Reinforcement Learning (RL) has emerged as a powerful tool for neural optimization, enabling models learns that solve complex problems without requiring expert knowledge.<n>Despite significant progress, existing RL approaches face challenges such as diminishing reward signals and inefficient exploration in vast action spaces.<n>We propose Preference Optimization, a novel method that transforms quantitative reward signals into qualitative preference signals via statistical comparison modeling.
  arXiv  Detail & Related papers  (2025-05-13T16:47:00Z)
• Scalable Chain of Thoughts via Elastic Reasoning [61.75753924952059]
  Elastic Reasoning is a novel framework for scalable chain of thoughts.<n>It separates reasoning into two phases--thinking and solution--with independently allocated budgets.<n>Our approach produces more concise and efficient reasoning even in unconstrained settings.
  arXiv  Detail & Related papers  (2025-05-08T15:01:06Z)
• Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization [86.56120216550232]
  We propose a novel two-stage framework for adaptive and efficient reasoning.<n>First, we construct a hybrid reasoning model by merging long and short CoT models.<n>Second, we apply bi-level preference training to guide the model to select suitable reasoning styles.
  arXiv  Detail & Related papers  (2025-04-30T14:01:45Z)
• A NotSo Simple Way to Beat Simple Bench [0.0]
  This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs)<n>We propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness.<n>Our results reveal model-specific strengths: Claude excels in maintaining logical consistency, while GPT-4o exhibits exploratory creativity but struggles with ambiguous prompts.
  arXiv  Detail & Related papers  (2024-12-12T16:04:31Z)
• Hierarchical Preference Optimization: Learning to achieve goals via feasible subgoals prediction [71.81851971324187]
  This work introduces Hierarchical Preference Optimization (HPO), a novel approach to hierarchical reinforcement learning (HRL) HPO addresses non-stationarity and infeasible subgoal generation issues when solving complex robotic control tasks. Experiments on challenging robotic navigation and manipulation tasks demonstrate impressive performance of HPO, where it shows an improvement of up to 35% over the baselines.
  arXiv  Detail & Related papers  (2024-11-01T04:58:40Z)
• An Efficient Approach for Solving Expensive Constrained Multiobjective Optimization Problems [0.0]
  An efficient probabilistic selection based constrained multi-objective EA is proposed, referred to as PSCMOEA. It comprises novel elements such as (a) an adaptive search bound identification scheme based on the feasibility and convergence status of evaluated solutions. Numerical experiments are conducted on an extensive range of challenging constrained problems using low evaluation budgets to simulate ECMOPs.
  arXiv  Detail & Related papers  (2024-05-22T02:32:58Z)
• Simplified Swarm Optimization for Bi-Objection Active Reliability Redundancy Allocation Problems [1.5990720051907859]
  The reliability redundancy allocation problem (RRAP) is a well-known problem in system design, development, and management. In this study, a bi-objective RRAP is formulated by changing the cost constraint as a new goal. To solve the proposed problem, a new simplified swarm optimization (SSO) with a penalty function, a real one-type solution structure, a number-based self-adaptive new update mechanism, a constrained non-dominated solution selection, and a new pBest replacement policy is developed.
  arXiv  Detail & Related papers  (2020-06-17T13:15:44Z)

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.