Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) often produce unnecessarily long explanations that reduce efficiency. |
| Approach: | They propose a length-aware reward that selectively penalizes insignificance tokens . they also propose 'dynamic length control' that encourages more detailed reasoning . |
| Outcome: | The proposed method reduces response length while maintaining correctness, the authors show . it selectively penalizes insignificance tokens while maintaining accuracy . |
Similar Papers
Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps. |
| Approach: | They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps . |
| Outcome: | The proposed framework reduces token usage by 69.7% on AIME24. |
Token-Budget-Aware LLM Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to enhance reasoning capabilities of large language models incur significant overhead in token usage, leading to increased costs. |
| Approach: | They propose a token-budget-aware LLM reasoning framework that adjusts the number of reasoning tokens based on the reasoning complexity of each problem. |
| Outcome: | The proposed method reduces token costs in CoT reasoning with only a slight performance reduction. |
Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) increase test-time computation, often in the form of chain-of-thought (CoT) however, reasoning traces can become unnecessarily long, increasing computation costs without improving accuracy and sometimes even degrading performance. |
| Approach: | They propose a multi-stage efficient reasoning method that combines supervised fine-tuning with reinforcement learning using an adaptive length penalty. |
| Outcome: | The proposed method reduces response length by an average of 28% for 8B models and 40% for 32B models while incurring only minor performance drops of 1.6 and 2.5 points, respectively. |
The Impact of Reasoning Step Length on Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Long reasoning steps in LLMs improve reasoning abilities, but the correlation between their effectiveness and the length of reasoning steps remains largely unknown. |
| Approach: | They conducted experiments that expand and compress the rationale reasoning steps within CoT demonstrations while keeping all other factors constant. |
| Outcome: | The results show that lengthening the reasoning steps in prompts significantly enhances LLMs’ reasoning abilities across multiple datasets. |
LEASH: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to long reasoning traces are hard to tune and fail to adapt to evolving LLMs. |
| Approach: | They propose a reinforcement learning framework that optimizes the length of reasoning traces by a Lagrangian primal–dual method. |
| Outcome: | The proposed framework reduces the average reasoning length by 60% across diverse tasks while maintaining competitive performance. |
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy (2026.acl-industry)
Copied to clipboard
| Challenge: | Reasoning LLMs often spend tokens on long intermediate reasoning traces when solving new problems. |
| Approach: | They propose to store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration and retrieve these skills at inference time to guide future reasoning. |
| Outcome: | The proposed approach reduces reasoning tokens while improving overall performance on coding and mathematical reasoning tasks. |
Do LLMs Encode Functional Importance of Reasoning Tokens ? (2026.acl-long)
Copied to clipboard
| Challenge: | Existing compact reasoning approaches generate long reasoning chains, but they lack a mechanism to encode token-level functional importance for answer generation. |
| Approach: | They propose a procedure that iteratively removes reasoning tokens from models and prunes them to yield length-controlled reasoning chains. |
| Outcome: | The proposed procedure outperforms a frontier model at reasoning lengths and shows that attention scores predict greedy pruning ranks. |
AIPO: Adaptive Information Guided Token-Level Reinforcement Learning for Large Language Model Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing RLVR methods focus on all generated tokens rather than on which tokens contribute to reasoning. |
| Approach: | They propose to use a Random–Fourier approximation of the Hilbert–Schmidt Independence Criterion to focus updates on decisive tokens discovered on the fly to improve the efficiency of mutual-information estimation. |
| Outcome: | The proposed approach yields +20% accuracy over strong RLVR baselines while updating merely 10% of tokens, demonstrating superior efficiency and effectiveness. |
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)
Copied to clipboard
Feng Luo, Yu-Neng Chuang, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu
| Challenge: | Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions. |
| Approach: | They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary. |
| Outcome: | The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy. |
Reinforced Efficient Reasoning via Semantically Diverse Exploration (2026.acl-long)
Copied to clipboard
Ziqi Zhao, Zhaochun Ren, Jiahong Zou, Liu Yang, Zhiwei Xu, Xuri Ge, Zhumin Chen, Xinyu Ma, Daiting Shi, Shuaiqiang Wang, Dawei Yin, Xin Xin
| Challenge: | Existing methods for reinforcement learning with verifiable rewards suffer from limited exploration diversity and inefficient reasoning. |
| Approach: | They propose a method that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains. |
| Outcome: | Extensive experiments on Qwen and Llama models validate the effectiveness and efficiency of ROSE. |