Recent LLMs have demonstrated sophisticated problem-solving capabilities on various benchmarks through advanced reasoning algorithms. However, the key research question of identifying reasoning steps that balance complexity and computational efficiency remains unsolved. Recent research has increasingly drawn upon psychological theories to explore strategies for optimizing cognitive pathways. The LLM's final outputs and intermediate steps are regarded as System 1 and System 2, respectively. However, an in-depth exploration of the System 2 reasoning is still lacking. Therefore, we propose a novel psychologically backed Scaffold Reasoning framework for code debugging, which encompasses the Scaffold Stream, Analytic Stream, and Integration Stream. The construction of reference code within the Scaffold Stream is integrated with the buggy code analysis results produced by the Analytic Stream through the Integration Stream. Our framework achieves an 88.91% pass rate and an average inference time of 5.36 seconds per-problem on DebugBench, outperforming other reasoning approaches across various LLMs in both reasoning accuracy and efficiency. Further analyses elucidate the advantages and limitations of various cognitive pathways across varying problem difficulties and bug types. Our findings also corroborate the alignment of the proposed Scaffold Reasoning framework with human cognitive processes.
Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal
Beihang University（北京航空航天大学）；Tsinghua University（清华大学）；BNRist（北京信息科学与技术国家研究中心）；Chinese Academy of Sciences（中国科学院）；Beijing Institute Of Technology（北京理工大学）
VeriPilot: An LLM-Powered Verilog Debugging Framework
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所国家专用集成电路设计实验室）；University of Chinese Academy of Sciences（中国科学院大学）；North China Electric Power University（华北电力大学）
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS（人工智能安全国家重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Alibaba Group（阿里巴巴集团）
University of Toronto（多伦多大学）；Nanyang Technological University（南洋理工大学）；Acceleration Consortium（加速联盟）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research (CIFAR)（加拿大高等研究院（CIFAR））；NVIDIA（英伟达）
QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院计算技术研究所处理器重点实验室，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
MCCoder: Streamlining Motion Control with LLM-Assisted Code Generation and Rigorous Verification
Thrust of Data Science and Analytics, The Hong Kong University of Science and Technology (Guangzhou)（数据科学与分析 thrust，香港科学与技术大学（广州））；Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology（工业工程与决策分析系，香港科学与技术大学）；MOVENSYS Inc.（MOVENSYS公司）；University of Cologne（科隆大学）
Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts
School of Data Science, Fudan University（复旦大学数据科学学院）；Shanghai Institute of Artificial Intelligence for Education, East China Normal University（华东师范大学教育人工智能研究所）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）；Ant Group（蚂蚁集团）
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Tencent AI Lab Seattle（腾讯人工智能实验室西雅图）；University of Maryland, College Park（马里兰大学帕克分校）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；City University of Hong Kong（香港城市大学）；Washington University in St. Louis（圣路易斯华盛顿大学）
