Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating redundant intermediate reasoning content. In this work, we argue that a major source of such redundancy is inefficient reflection, which often manifests in two problematic patterns: Indiscriminate Reflection, where the model performs broad, low-impact checks throughout reasoning, and Repetitive Reflection, where it repeatedly re-verifies an already established conclusion. To address this, we introduce a graph-based CoT optimization framework. Specifically, we convert each linear CoT into a directed acyclic graph (DAG) with explicit dependency edges, and design a dual pruning strategy: branch-level pruning removes weakly contributing reflection branches, while depth-level pruning eliminates late-stage re-verification. We distill this behavior via a three-stage pipeline: (1) SFT to initialize the policy on pruned concise traces, (2) DPO to prefer correct but less redundant trajectories, and (3) GRPO with length penalty to jointly optimize answer correctness and efficiency. Experiments show that our approach reduces the average reasoning tokens by 42\% while maintaining or improving accuracy.
MI-PRUN: Optimize Large Language Model Pruning via Mutual Information
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院)
CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(南京航空航天大学人工智能学院);The Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education(教育部脑机智能技术重点实验室)
Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning
Graduate School of Data Science, Seoul National University(数据科学研究生院,首尔国立大学);Department of Rural Systems Engineering, Seoul National University(农村系统工程系,首尔国立大学);Department of Aerospace Engineering, Seoul National University(航空航天工程系,首尔国立大学)
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
China Agriculture University(中国农业大学);Tsinghua University(清华大学);University of Oxford(牛津大学);Didichuxing Co. Ltd(滴滴出行有限公司);Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区);Nanyang Technological University(南洋理工大学)
Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院)
Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models
University of Trieste(的里雅斯特大学);University of Milano-Bicocca(米兰-比科卡大学);University of Groningen(格罗宁根大学);Khoury College of Computer Sciences, Northeastern University(东北大学科里计算机学院)
When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo(宁波数字孪生研究院,东方理工高等研究院,宁波);Viterbi School of Engineering, University of Southern California(南加州大学维特比工程学院);The Hong Kong Polytechnic University(香港理工大学);LMU Munich(慕尼黑大学);Saarland University(萨尔大学)
EvoP: Robust LLM Inference via Evolutionary Pruning
City University of Hong Kong(香港城市大学);Mohamed bin Zayed University of Artificial Intelligence(马尔代夫穆罕默德·本·扎耶德人工智能大学);Baidu(百度);National Taiwan University(国立台湾大学)
Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院)
Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合国家科学中心人工智能研究院)
CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院);School of Computer Science, Wuhan University(武汉大学计算机学院);School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机学院);Cognitive AI Lab, Shanghai Huawei Technologies, China(上海华为技术有限公司认知人工智能实验室)