Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement

• URL: http://arxiv.org/abs/2505.07961v3
• Date: Fri, 23 May 2025 04:50:59 GMT
• Title: Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement
• Authors: Xuechen Zhang, Zijian Huang, Chenshun Ni, Ziyang Xiong, Jiasi Chen, Samet Oymak,
• Abstract summary: 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.
• Score: 22.801244105119025
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and high computational cost, especially for small language models distilled with supervised fine-tuning (SFT). In this work, we propose new algorithms to improve token-efficient reasoning with small-scale models by effectively trading off accuracy and computation. 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. Verbosity also significantly varies across wrong vs correct responses. To address these issues, we propose two solutions: (1) Temperature scaling (TS) to control the stopping point for the thinking phase and thereby trace length, and (2) TLDR: a length-regularized reinforcement learning method based on GRPO that facilitates multi-level trace length control (e.g. short, medium, long reasoning). Experiments on four reasoning benchmarks, MATH500, AMC, AIME24 and OlympiadBench, demonstrate that TS is highly effective compared to s1's budget forcing approach and TLDR significantly improves token efficiency by about 50% with minimal to no accuracy loss over the SFT baseline. Moreover, TLDR also facilitates flexible control over the response length, offering a practical and effective solution for token-efficient reasoning in small models. Ultimately, our work reveals the importance of stopping time control, highlights shortcomings of pure SFT, and provides effective algorithmic recipes.

Related papers

• 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)
• EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models [42.49934375597466]
  Large Reasoning Models (LRMs) excel at complex reasoning tasks through extended chain-of-thought generation.<n>We find that the entropy of the model's output distribution in early reasoning steps reliably distinguishes correct from incorrect reasoning.<n>We propose EntroCut, a training-free method that dynamically truncates reasoning by identifying high-confidence states.
  arXiv  Detail & Related papers  (2026-01-30T06:19:16Z)
• 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)
• DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching [54.98126916293868]
  Large Reasoning Models (LRMs) produce excessively long chain-of-thought traces that degrade accuracy.<n>We propose a model-agnostic decoding framework that sketches the reasoning space by branching at high-entropy tokens and applies early stopping to select the shortest completed reasoning path.<n>This approach approximates the optimal solution that enhances both efficiency and accuracy, without requiring additional training or supervision.
  arXiv  Detail & Related papers  (2025-11-01T17:41:28Z)
• Boosting Accuracy and Efficiency of Budget Forcing in LLMs via Reinforcement Learning for Mathematical Reasoning [1.4348015996689416]
  We propose a framework integrating reinforcement learning (RL) to improve token efficiency and boost the performance of a 1.5B model for mathematical reasoning.<n>Our main findings showed an overall higher accuracy while significantly reducing its token usage by over 40% compared to the SFT model.
  arXiv  Detail & Related papers  (2025-10-24T12:39:15Z)
• Towards Flash Thinking via Decoupled Advantage Policy Optimization [11.025775055262569]
  Large Reasoning Models (LRMs) have achieved remarkable performance in solving complex problems via supervised fine-tuning (SFT) and reinforcement learning (RL)<n>Existing RL algorithms suffer from excessively lengthy responses and overthinking issues, resulting in increased inference latency and computational consumption.<n>We propose a novel RL framework, DEPO, to reduce inefficient reasoning for models.
  arXiv  Detail & Related papers  (2025-10-17T07:19:20Z)
• SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control [5.224609066309358]
  Large reasoning models (LRMs) have exhibited remarkable reasoning capabilities through inference-time scaling.<n>Previous work has attempted to mitigate this issue by penalizing the overall length of generated samples during reinforcement learning.<n>We propose SmartThinker, a two-stage learnable framework designed to enable fine-grained control over the length of reasoning chains.
  arXiv  Detail & Related papers  (2025-07-06T11:21:47Z)
• 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)
• Kinetics: Rethinking Test-Time Scaling Laws [18.325591438335007]
  Kinetics Scaling Law suggests that test-time compute is more effective when used on models above a threshold than smaller ones.<n>Motivated by this, we propose a new scaling paradigm centered on sparse attention, which lowers per-token cost and enables longer generations and more parallel samples.
  arXiv  Detail & Related papers  (2025-06-05T17:59:24Z)
• TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression [55.37723860832064]
  We propose a dynamic ratio-based training pipeline that does not rely on sophisticated data annotations.<n>We validate our approach across models on DeepSeek-R1-Distill-7B and DeepSeek-R1-Distill-14B and on a diverse set of benchmarks with varying difficulty levels.
  arXiv  Detail & Related papers  (2025-06-03T09:23:41Z)
• CoThink: Token-Efficient Reasoning via Instruct Models Guiding Reasoning Models [56.40065909544213]
  Large language models (LLMs) benefit from increased test-time compute, a phenomenon known as test-time scaling.<n>However, reasoning-optimized models often overthink even simple problems, producing excessively verbose outputs and leading to low token efficiency.<n>We identify two key causes of this verbosity: (1) reinforcement learning reduces the information density of forward reasoning, and (2) backward chain-of thought training encourages redundant and often unnecessary verification steps.
  arXiv  Detail & Related papers  (2025-05-28T06:24:45Z)
• LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling [29.721108461390973]
  We introduce PIR (Perplexity-based Importance Refinement), a principled framework that quantitatively evaluates the importance of each reasoning step.<n>PIR identifies and selectively prunes only low-importance functional steps while preserving progressive reasoning components.<n>Our approach demonstrates strong generalizability across different model sizes, data sources, and token budgets.
  arXiv  Detail & Related papers  (2025-05-25T15:17:57Z)
• Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens [51.90059610606049]
  This paper revisits the efficiency of such reasoning processes through an information-theoretic lens.<n>We propose two metrics, InfoBias and InfoGain, to quantify divergence from ideal reasoning paths and stepwise information contribution.<n>Motivated by these findings, we introduce an entropy-based Adaptive Think strategy that dynamically halts reasoning once confidence is sufficiently high.
  arXiv  Detail & Related papers  (2025-05-23T13:38:56Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Dynamic Early Exit in Reasoning Models [14.508648537186989]
  Overthinking in long chain-of-thought (CoT) generation slows down the efficiency of problem solving.<n>We propose a method that allows LLMs to self-truncate CoT sequences by early exit during generation.<n>Our method requires no additional training and can be seamlessly integrated into existing o1-like reasoning LLMs.
  arXiv  Detail & Related papers  (2025-04-22T13:36:53Z)
• 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)
• When More is Less: Understanding Chain-of-Thought Length in LLMs [53.77747102201451]
  Chain-of-thought (CoT) reasoning enhances the multi-step reasoning capabilities of large language models (LLMs)<n>However, for most models and tasks, does an increase in CoT length consistently lead to improved reasoning accuracy?<n>In this paper, we observe a nuanced relationship: as the number of reasoning steps increases, performance initially improves but eventually decreases.
  arXiv  Detail & Related papers  (2025-02-11T05:28:59Z)
• 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)

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.