HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization

• URL: http://arxiv.org/abs/2505.11225v1
• Date: Fri, 16 May 2025 13:21:28 GMT
• Title: HAPO: Training Language Models to Reason Concisely via History-Aware Policy Optimization
• Abstract summary: We present History-Aware Policy Optimization (HAPO), which keeps track of a history state for each problem.<n>HAPO employs a novel length reward function based on this history state to incentivize the discovery of correct solutions.<n>Experiment results demonstrate that HAPO effectively induces LLMs' concise reasoning abilities, producing length reductions of 33-59% with accuracy drops of only 2-5%.
• Score: 17.844933477135523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While scaling the length of responses at test-time has been shown to markedly improve the reasoning abilities and performance of large language models (LLMs), it often results in verbose outputs and increases inference cost. Prior approaches for efficient test-time scaling, typically using universal budget constraints or query-level length optimization, do not leverage historical information from previous encounters with the same problem during training. We hypothesize that this limits their ability to progressively make solutions more concise over time. To address this, we present History-Aware Policy Optimization (HAPO), which keeps track of a history state (e.g., the minimum length over previously generated correct responses) for each problem. HAPO employs a novel length reward function based on this history state to incentivize the discovery of correct solutions that are more concise than those previously found. Crucially, this reward structure avoids overly penalizing shorter incorrect responses with the goal of facilitating exploration towards more efficient solutions. By combining this length reward with a correctness reward, HAPO jointly optimizes for correctness and efficiency. We use HAPO to train DeepSeek-R1-Distill-Qwen-1.5B, DeepScaleR-1.5B-Preview, and Qwen-2.5-1.5B-Instruct, and evaluate HAPO on several math benchmarks that span various difficulty levels. Experiment results demonstrate that HAPO effectively induces LLMs' concise reasoning abilities, producing length reductions of 33-59% with accuracy drops of only 2-5%.

Related papers

• Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning [21.035897836243915]
  Large Reasoning Models (LRMs) have shown exceptional reasoning capabilities, but they also suffer from the issue of overthinking.<n>For problems that exceed the model's capabilities, LRMs tend to exhibit the overconfidence phenomenon, generating overly short but incorrect answers.<n>We propose Difficulty-Differentiated Policy Optimization (DDPO), an efficient reinforcement learning algorithm that optimize simple and complex tasks separately.
  arXiv  Detail & Related papers  (2026-03-19T06:30:26Z)
• SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning [34.14269693187003]
  We propose SmartThinker, a novel efficient reasoning method with progressive CoT length calibration.<n>Experiment results show that SmartThinker achieves up to 52.5% average length compression with improved accuracy.
  arXiv  Detail & Related papers  (2026-03-09T06:08:14Z)
• Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model [12.881680088950008]
  Leash is a reinforcement learning framework for efficient reasoning in LLMs.<n>Leash reduces the average reasoning length by 60% across diverse tasks.<n>Our work thus presents a practical and effective paradigm for developing controllable and efficient LLMs.
  arXiv  Detail & Related papers  (2025-12-25T07:16:26Z)
• TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs [57.217593337454026]
  TokenSqueeze is a novel Long2Short method that condenses reasoning paths while preserving performance and relying exclusively on self-generated data.<n>We show that TokenSqueeze reduces token usage while maintaining accuracy on the MATH500 benchmark.
  arXiv  Detail & Related papers  (2025-11-17T10:38:56Z)
• DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning [134.03095505580276]
  Doing Length pEnalty Right (DLER) is a training recipe combining batch-wise reward normalization, higher clipping, dynamic sampling, and a simple truncation length penalty.<n>DLER achieves state-of-the-art accuracy--efficiency trade-offs, cutting output length by over 70 percent while surpassing all previous baseline accuracy.
  arXiv  Detail & Related papers  (2025-10-16T20:05:57Z)
• Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding [59.60915947702282]
  Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs)<n>Existing RLVR methods often suffer from exploration inefficiency due to mismatches between the training data's difficulty and the model's capability.<n>We propose SEELE, a novel supervision-aided RLVR framework that dynamically adjusts problem difficulty to stay within the high-efficiency region.
  arXiv  Detail & Related papers  (2025-09-08T17:36:21Z)
• Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization [26.462701299259248]
  Large Reasoning Models (LRMs) have demonstrated strong performance on complex tasks through long Chain-of-Thought (CoT) reasoning.<n>Their lengthy outputs increase computational costs and may lead to overthinking, raising challenges in balancing reasoning effectiveness and efficiency.<n>This paper investigates efficient methods to reduce the generation length of LRMs.
  arXiv  Detail & Related papers  (2025-08-13T20:00:09Z)
• $\ exttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts [55.231201692232894]
  $textttSPECS$ is a latency-aware test-time scaling method inspired by speculative decoding.<n>Our results show that $textttSPECS$matches or surpasses beam search accuracy while reducing latency by up to $sim$19.1%.
  arXiv  Detail & Related papers  (2025-06-15T05:50:05Z)
• Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty [13.843606627539597]
  This study seeks to enhance the efficiency of large language models (LLMs) by promoting conciseness for simpler problems.<n>We manage the model's reasoning efficiency by dividing the reward function and including a novel penalty for output length.<n>Our approach has yielded impressive outcomes in benchmark evaluations across three datasets: GSM8K, MATH500, and AIME2024.
  arXiv  Detail & Related papers  (2025-06-12T07:49:24Z)
• Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards [17.829990749622496]
  We propose an adaptive reward-shaping method for large language models.<n>Our method dynamically adjusts the trade-off between accuracy and response length based on model performance.<n> Experiments show that our approach consistently and dramatically reduces reasoning length while largely maintaining accuracy.
  arXiv  Detail & Related papers  (2025-05-23T18:44:46Z)
• Learn to Reason Efficiently with Adaptive Length-based Reward Shaping [23.626013831589212]
  Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL)<n>We present a unified framework that formulates various efficient reasoning methods through the lens of length-based reward shaping.<n>Experiments on DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, and DeepSeek-R1-Distill-Qwen-32B show that our approach significantly enhances both reasoning performance and response length efficiency.
  arXiv  Detail & Related papers  (2025-05-21T15:03:26Z)
• Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement [22.801244105119025]
  We propose new algorithms to improve token-efficient reasoning with small-scale models by effectively trading off accuracy and computation.<n>We first show that the post-SFT model fails to determine the optimal stopping point of the reasoning process, resulting in verbose and repetitive outputs.<n>Experiments on four reasoning benchmarks, MATH500, AMC, AIME24 and OlympiadBench, demonstrate that TS is highly effective compared to s1's budget forcing approach.
  arXiv  Detail & Related papers  (2025-05-12T18:04:39Z)
• AdaR1: From Long-CoT to 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)
• Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning [60.67176246634741]
  We formalize the problem of optimizing test-time compute as a meta-reinforcement learning (RL) problem.<n>We show that state-of-the-art models do not minimize regret, but one can do so by maximizing a dense reward bonus in conjunction with the outcome 0/1 reward RL.
  arXiv  Detail & Related papers  (2025-03-10T17:40:43Z)
• O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning [98.3430004984531]
  We propose Length-Harmonizing Fine-Tuning (O1-Pruner) to minimize reasoning overhead while maintaining accuracy.<n>Our code is coming soon at https://github.com/StarDewXXX/O1-Pruner.
  arXiv  Detail & Related papers  (2025-01-22T01:35:11Z)
• Disentangling Length from Quality in Direct Preference Optimization [93.74831404396174]
  Reinforcement Learning from Human Feedback (RLHF) has been a crucial component in the recent success of Large Language Models. RLHF is know to exploit biases in human preferences, such as verbosity. We develop a principled but simple regularization strategy that prevents length exploitation, while still maintaining improvements in model quality.
  arXiv  Detail & Related papers  (2024-03-28T06:03:47Z)
• A Long Way to Go: Investigating Length Correlations in RLHF [59.49656695716066]
  This paper demonstrates, on three diverse settings, that optimizing for response length is a significant factor behind RLHF. We find improvements in reward to largely be driven by increasing response length, instead of other features. Even a purely length-based reward reproduces most downstream RLHF improvements over supervised fine-tuned models.
  arXiv  Detail & Related papers  (2023-10-05T17:38:28Z)

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.