How Far Are We from Optimal Reasoning Efficiency?

• URL: http://arxiv.org/abs/2506.07104v1
• Date: Sun, 08 Jun 2025 12:18:50 GMT
• Title: How Far Are We from Optimal Reasoning Efficiency?
• Authors: Jiaxuan Gao, Shu Yan, Qixin Tan, Lu Yang, Shusheng Xu, Wei Fu, Zhiyu Mei, Kaifeng Lyu, Yi Wu,
• Abstract summary: Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning.<n>LRMs often produce excessively verbose and redundant reasoning traces.<n>Existing fine-tuning methods aim to improve reasoning efficiency, but assessing their efficiency gains remains challenging.
• Score: 22.726975408299822
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency incurs high inference costs and limits practical deployment. While existing fine-tuning methods aim to improve reasoning efficiency, assessing their efficiency gains remains challenging due to inconsistent evaluations. In this work, we introduce the reasoning efficiency frontiers, empirical upper bounds derived from fine-tuning base LRMs across diverse approaches and training configurations. Based on these frontiers, we propose the Reasoning Efficiency Gap (REG), a unified metric quantifying deviations of any fine-tuned LRMs from these frontiers. Systematic evaluation on challenging mathematical benchmarks reveals significant gaps in current methods: they either sacrifice accuracy for short length or still remain inefficient under tight token budgets. To reduce the efficiency gap, we propose REO-RL, a class of Reinforcement Learning algorithms that minimizes REG by targeting a sparse set of token budgets. Leveraging numerical integration over strategically selected budgets, REO-RL approximates the full efficiency objective with low error using a small set of token budgets. Through systematic benchmarking, we demonstrate that our efficiency metric, REG, effectively captures the accuracy-length trade-off, with low-REG methods reducing length while maintaining accuracy. Our approach, REO-RL, consistently reduces REG by >=50 across all evaluated LRMs and matching Qwen3-4B/8B efficiency frontiers under a 16K token budget with minimal accuracy loss. Ablation studies confirm the effectiveness of our exponential token budget strategy. Finally, our findings highlight that fine-tuning LRMs to perfectly align with the efficiency frontiers remains an open challenge.

Related papers

• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• Conformal Thinking: Risk Control for Reasoning on a Compute Budget [60.65072883773352]
  Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases.<n>We re-frame the budget setting problem as risk control, limiting the error rate while minimizing compute.<n>Our framework introduces an upper threshold that stops reasoning when the model is confident and a novel lower threshold that preemptively stops unsolvable instances.
  arXiv  Detail & Related papers  (2026-02-03T18:17:22Z)
• Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data [57.996437077411315]
  We study the reasoning behavior of large language models (LLMs) under limited computation budgets.<n>We introduce an anytime reasoning framework and the Anytime Index, a metric that quantifies how effectively solution quality improves as reasoning tokens increase.<n> Experiments on NaturalPlan (Trip), AIME, and GPQA datasets show consistent gains across Grok-3, GPT-oss, GPT-4.1/4o, and LLaMA models.
  arXiv  Detail & Related papers  (2026-01-16T07:09:30Z)
• DEPO: Dual-Efficiency Preference Optimization for LLM Agents [75.6723341304463]
  We propose DEPO, a dual-efficiency preference optimization method that jointly rewards succinct responses and fewer action steps.<n>Experiments on WebShop and BabyAI show that DEPO cuts token usage by up to 60.9% and steps by up to 26.9%, while achieving up to a 29.3% improvement in performance.
  arXiv  Detail & Related papers  (2025-11-19T12:38:43Z)
• PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning [33.71268958080582]
  Large reasoning models (LRMs) have achieved remarkable progress in complex problem-solving tasks.<n>LRMs typically suffer from high computational costs during deployment.<n>We propose Probably Approximately Correct (PAC) reasoning that controls the performance loss under the user-specified performance loss tolerance.
  arXiv  Detail & Related papers  (2025-10-10T08:33:47Z)
• Promoting Efficient Reasoning with Verifiable Stepwise Reward [7.385337642642193]
  Large reasoning models (LRMs) have recently achieved significant progress in complex reasoning tasks, aided by reinforcement learning.<n>LRMs often suffer from overthinking, expending excessive computation on simple problems and reducing efficiency.<n>We propose a novel rule-based verifiable stepwise reward mechanism (VSRM), which assigns rewards based on the performance of intermediate states in the reasoning trajectory.
  arXiv  Detail & Related papers  (2025-08-14T02:43:53Z)
• 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)
• 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)
• Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs [8.359909829007005]
  We investigate whether efficient reasoning strategies introduce behavioral inconsistencies in large reasoning models (LRMs)<n>$ICBENCH$ is a benchmark designed to measure inconsistency in LRMs across three dimensions.<n>We find that while larger models generally exhibit greater consistency than smaller ones, they all display widespread "scheming" behaviors.
  arXiv  Detail & Related papers  (2025-06-24T10:25:28Z)
• 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)
• Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively [13.40488551654639]
  We introduce the 3E Criteria to assess the cost-effectiveness of search strategies.<n>We propose the Speculative Reward Model (SRM), a plug-and-play framework that integrates seamlessly with existing search strategies.<n> Experimental results show that RM reduces costs to 1/10 of the original search framework on average while maintaining effectiveness.
  arXiv  Detail & Related papers  (2025-05-31T05:32:12Z)
• 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)
• When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning [20.233873556056487]
  Large reasoning models (LRMs) achieve remarkable performance via long reasoning chains, but often incur excessive computational overhead due to redundant reasoning.<n>We propose Adaptive Self-Recovery Reasoning (ASRR), a framework that suppresses unnecessary reasoning and enables implicit recovery.<n>Our results highlight the potential of ASRR for enabling efficient, adaptive, and safer reasoning in LRMs.
  arXiv  Detail & Related papers  (2025-05-21T11:41:39Z)
• Optimizing Anytime Reasoning via Budget Relative Policy Optimization [70.32755424260336]
  We present a novel framework, AnytimeReasoner, to optimize anytime reasoning performance.<n>We truncate the complete thinking process to fit within sampled token budgets from a prior distribution.<n>We then optimize the thinking and summary policies in a decoupled manner to maximize the cumulative reward.
  arXiv  Detail & Related papers  (2025-05-19T17:58:44Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs)<n>RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness.<n>RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead [24.611413814466978]
  Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. Existing methods to enhance context awareness are often inefficient, incurring time or memory overhead during inference. We propose Position-Embedding-Agnostic attention Re-weighting (PEAR) which enhances the context awareness of LLMs with zero inference overhead.
  arXiv  Detail & Related papers  (2024-09-29T15:40:54Z)
• Lower-Left Partial AUC: An Effective and Efficient Optimization Metric for Recommendation [52.45394284415614]
  We propose a new optimization metric, Lower-Left Partial AUC (LLPAUC), which is computationally efficient like AUC but strongly correlates with Top-K ranking metrics. LLPAUC considers only the partial area under the ROC curve in the Lower-Left corner to push the optimization focus on Top-K.
  arXiv  Detail & Related papers  (2024-02-29T13:58:33Z)
• Large-scale Optimization of Partial AUC in a Range of False Positive Rates [51.12047280149546]
  The area under the ROC curve (AUC) is one of the most widely used performance measures for classification models in machine learning. We develop an efficient approximated gradient descent method based on recent practical envelope smoothing technique. Our proposed algorithm can also be used to minimize the sum of some ranked range loss, which also lacks efficient solvers.
  arXiv  Detail & Related papers  (2022-03-03T03:46:18Z)
• False Correlation Reduction for Offline Reinforcement Learning [115.11954432080749]
  We propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL)
  arXiv  Detail & Related papers  (2021-10-24T15:34:03Z)

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.