LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

• URL: http://arxiv.org/abs/2605.09806v1
• Date: Sun, 10 May 2026 23:05:02 GMT
• Title: LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
• Abstract summary: Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve.<n>These inflated Chain-of-Length trajectories (CoT) often exceed what the underlying problems require, wasting compute, latency, and context budgets.<n>We propose LEAD (Thought-Efficient Adaptive and Dynamic reasoning), a method that replaces statics with online, self-adaptive mechanisms.
• Score: 24.128148876541783
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require, wasting compute, latency, and context budgets. While introducing length-based efficiency rewards during reinforcement learning offers a natural remedy, existing methods struggle with two fundamental challenges: the optimal balance between correctness and efficiency is non-stationary throughout training, and intrinsic reasoning budgets vary drastically across problems. Relying on static reward weights and global length constraints inevitably forces a compromise between degraded accuracy and unrealized compression. To overcome these limitations, we propose LEAD (Length-Efficient Adaptive and Dynamic reasoning), a method that replaces static heuristics with online, self-adaptive mechanisms. LEAD dynamically calibrates the correctness-efficiency trade-off at each step using a Potential-Scaled Instability, directing optimization capacity to the most informative learning signal. Furthermore, it estimates an adaptive per-problem target length online based on the model's own correct rollouts, applying a symmetric efficiency reward that penalizes both overthinking and over-compression. Evaluated on five mathematical reasoning benchmarks, LEAD achieves the highest accuracy and Accuracy-Efficiency Score among RL-trained efficient-reasoning methods while producing substantially shorter outputs than the base model.

Related papers

• CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models [18.894895416263296]
  Confidence-Adaptive Thinking (CAT) is a framework that incorporates the model's intrinsic self-certainty signals as confidence into the preference optimization process.<n>Our work enables LRMs to effectively compress confident responses while deliberating on uncertain ones, offering a potentially robust solution for balancing accuracy and latency in practical industrial scenarios.
  arXiv  Detail & Related papers  (2026-07-01T12:27:14Z)
• Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards [33.82648880607807]
  Group Relative Policy Optimization (GRPO) aims to reduce verbosity.<n> GRPO's group normalization creates divergent advantages when incorrect answers receive continuous length penalties.<n>To robustly prevent both failure modes, we propose ACOER.
  arXiv  Detail & Related papers  (2026-06-21T23:27:12Z)
• ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models [48.426487984321675]
  Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost.<n>Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability.<n>We propose Adaptive Dual-Process Thinking (ADaPT), a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training.
  arXiv  Detail & Related papers  (2026-06-18T08:11:45Z)
• SuCo: Sufficiency-guided Continuous Adaptive Reasoning [59.17222918775686]
  Large Reasoning Models (LRMs) often generate excessively long Chain-of-Thoughts (CoT)<n>Existing efforts to mitigate this inefficiency typically rely on discrete reasoning modes or fixed budget tiers.<n>We introduce Minimal Sufficient CoT (MSC), defined as the shortest prefix of a CoT trajectory which is adequate for producing the correct answer.
  arXiv  Detail & Related papers  (2026-06-16T08:52:15Z)
• Stabilizing Efficient Reasoning with Step-Level Advantage Selection [54.563811052329235]
  We show that short-context post-training alone, using standard GRPO without any length-aware objective, already induces substantial reasoning compression.<n>We propose Step-level Advantage Selection (SAS), which operates at the reasoning-step level and assigns a zero advantage to low-confidence steps in correct rollouts and to high-confidence steps in verifier-failed rollouts.
  arXiv  Detail & Related papers  (2026-04-27T03:34:59Z)
• Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation [14.501114943020589]
  Large reasoning models (LRMs) achieve strong performance through extended reasoning traces.<n>LRMs often exhibit overthinking behavior for low-complexity queries.<n>We propose a two-stage framework for stable adaptive thinking in LRMs.
  arXiv  Detail & Related papers  (2026-02-26T02:49:36Z)
• Constraint-Rectified Training for Efficient Chain-of-Thought [60.52883907721588]
  Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs)<n>While longer reasoning traces can improve answer quality and unlock abilities such as self-correction, they also incur high inference costs and often introduce redundant steps, known as overthinking.<n>Recent research seeks to develop efficient reasoning strategies that balance reasoning length and accuracy.
  arXiv  Detail & Related papers  (2026-02-13T02:13:45Z)
• Training-free Context-adaptive Attention for Efficient Long Context Modeling [57.703159205740185]
  Training-free Context-adaptive Attention (TCA-Attention) is a training-free sparse attention mechanism that selectively attends to only the informative tokens for efficient long-context inference.<n>TCA-Attention achieves a 2.8$times$ speedup and reduces KV cache by 61% at 128K context length while maintaining performance comparable to full attention.
  arXiv  Detail & Related papers  (2025-12-10T01:54:57Z)
• DART: Difficulty-Adaptive Reasoning Truncation for Efficient Large Language Models [36.962276192354174]
  textbfDART adjusts thinking length according to problem difficulty.<n>textbfTruncation framework learns when to stop thinking''
  arXiv  Detail & Related papers  (2025-11-03T02:41:20Z)
• 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)
• Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models [38.225442399592936]
  We introduce the Dynamic Reasoning-Boundary Self-Awareness Framework (DR. SAF)<n>DR. SAF integrates three key components: Boundary Self-Awareness Alignment, Adaptive Reward Management, and a Boundary Preservation Mechanism.<n>Our experimental results demonstrate that DR. SAF achieves a 49.27% reduction in total response tokens with minimal loss in accuracy.
  arXiv  Detail & Related papers  (2025-08-15T16:40:29Z)
• LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization [48.91511514636768]
  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%.
  arXiv  Detail & Related papers  (2025-07-21T16:14:41Z)
• AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control [18.273777938294327]
  Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts.<n>We introduce AALC, a lightweight, accuracy-aware length reward integrated into reinforcement learning.<n>We show that our approach reduces response length by over 50% while maintaining or even improving the original accuracy.
  arXiv  Detail & Related papers  (2025-06-25T06:29:18Z)
• 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)

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.