赵冰｜宁波大学｜学者主页

期刊论文

2026

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

Chuan Xiao, Zheng-Bo Jiao, Shao-Bo Wang, Wei Wang, Bing Zhao, Hu Wei, Lin-Feng Zhang, Lin Qu

arXiv.org

DOI

2026

Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning

Le-Xiang Tang, Weihao Gao, Bing Zhao, Lu Ma, Qiao Jin, Bang Yang, Yuexian Zou

arXiv.org

DOI

2026

Discovering Millions of Interpretable Features with Sparse Autoencoders

Xinyang He, Wei Wang, Bing Zhao, Xuan-Cheng Ren, Wen-Bo Li, Wei Qiao, Hu Wei, Lin Qu

arXiv.org

DOI

2026

Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement

Mingyu Xu, Cheng Fang, Keyue Jiang, Yuqian Zheng, Yang-Hua Xiao, Bao-Jian Zhou, Qifang Zhao, Suhang Zheng, Xiuwen Zhu, Jiyang Tang, Yong-Chi Zhao, Yijia Luo, Zhi-Qi Bai, Yu-Chi Xu, Wen-Bo Su, Wei Wang, Bing Zhao, Lin Qu, Xiao-Xiao Xu

arXiv.org

DOI

2026

Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation

Niantong Li, Guang Hu, Wei Qiao, Ying Ba, Qi-Chen Hong, Shiju Shen, Jin-Lin Wang, Fan Zhou, Jian Kang, Xin Shang, Zi-Yi He, Wei Wang, Da-Lin Li, Jiahao Li, Jie Zhang, Kai-Yuan Gao, Kun Yan, Lihan Jiang, Ning-Yuan Tang, Shengming Yin, Tian-He Wu, Xiao Xu, Xiaoyu Chen, Yuxiang Chen, Yan Shu, Yanran Zhang, Yi-Lei Chen, Yi-Xian Xu, Zekai Zhang, Zhen-Dong Wang, Zihao Liu, Zi-Kai Zhou, Hongzhu Shi, Yi Wang, Bing Zhao, Huayun Wei, Lin Qu, Chen-Fei Wu

arXiv.org

DOI

2026

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis

Zheng-Bo Jiao, Shao-Bo Wang, Zifan Zhang, Xuan Ren, Wei Wang, Bing Zhao, Hu Wei, Lin-Feng Zhang

arXiv.org

DOI

2026

ClinConsensus: A Consensus-Based Benchmark for Evaluating Chinese Medical LLMs across Difficulty Levels

Xiang Zheng, Hang Li, Wenjie Luo, Wei-Qi Zhai, Yi-Yuan Li, Chuanmiao Yan, Tian-Yi Tang, Yu-Bo Ma, Ke-Xin Yang, Dayiheng Liu, Huijie Wei, Bing Zhao

arXiv.org

DOI

2026

BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs

Benoît Wang, Xiao-Gang Li, Ruo-Chen Gao, Peiyao Xiao, Cheng-Liang Xu, Zeyu Wang, Zichao Chen, Bing Zhao, Hu Wei

arXiv.org

DOI

2026

PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice

Yuzhen Shi, Huang-Hai Liu, Yi-Ran Hu, Gao-Jie Song, Xinran Xu, Yu-Bo Ma, Tian-Yi Tang, Li Zhang, Qing-Jing Chen, Di Feng, Wenbo Lv, Weiheng Wu, Ke-Xin Yang, Sen Yang, Wei Wang, Rong Shi, Yu-Ping Qiu, Yu Qi, Jing-Wen Zhang, Xiao-Yu Sui, Yifan Chen, Yi Zhang, An Yang, Bo-Wen Yu, Dayiheng Liu, Jun-Yang Lin, Wei-Xing Shen, Bing Zhao, C. L. Clarke, Huajie Wei

Annual Meeting of the Association for Computational Linguistics

DOI

2026

MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning

Ling-Yan Wu, Xiang-Xiang Zheng, Wei-Qi Zhai, Wei Wang, Xuanhua Ren, Zifan Zhang, Hu Wei, Bing Zhao

arXiv.org

DOI

2026

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning

Zheng-Bo Jiao, Shao-Bo Wang, Zifan Zhang, Wei Wang, Bing Zhao, Hu Wei, Lin-Feng Zhang

arXiv.org

DOI

2026

DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning

Hao-Xiang Sun, Lizhen Xu, Bing Zhao, Wo-Tao Yin, Wei Wang, Bo-Yu Yang, Rui Wang, Hu Wei

arXiv.org

DOI

2026

ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

Bing-Chen Pei, Li-Chong Chen, Bing Zhao, Zi-Jie Wu, Si-Rui Wang, Min Zhang, Yan-Hao Chen, Qing-Xu Liu, Qi-Huang Gao, Chang-Tien Lu, Bo Gao

2026

Living-Harness Is an Interactive-Agent Evolver

Yue-Tian Du, Yu-Cheng Wang, Helsing Xu, Jiexu Xu, Shan-Wen Tan, Bing Zhao, Bo-Yu Yang, Zhijie Xu, Ming Kong, Hu Wei, Jie Liu, Qiang Zhu

arXiv.org

DOI

2026

GSDiffRec: Enhancing Personalized Sequential Recommendation via Diffusion Augmentation and Guidance Optimization

Ruxue Han, Lian-Yong Qi, Chao Yan, Weiyi Zhong, Boyuan Yan, Bing Zhao, Xiao-Ran Zhao, Zhikang Feng, Xiao-Long Xu, Hao-Long Xiang, Xu-Yun Zhang

Web Search and Data Mining

DOI

2026

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction

Zheng-Bo Jiao, Shao-Bo Wang, Zifan Zhang, Wei Wang, Bing Zhao, Hu Wei, Lin-Feng Zhang

arXiv.org

DOI

2026

Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery

Tianyun Zhong, Wangyi Jiang, Wei Wang, Xuanang Chen, Yaojie Lu, Shi-Wei Ye, Yuzhen Shi, Bo-Yu Yang, Jing-Hang Wang, Hanchang Li, Wei-Qi Zhai, Bing Zhao, Hu Wei, Haiyang Yu, Yong-Bin Li, Hong-Yu Lin, Le Sun, Xian-Pei Han

arXiv.org

DOI

2026

Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements

Xin Tong, Xuanming Zhang, Tian-Yi Tang, An Yang, Jiatu Hu, Guojie Lin, Zhenzhen Shi, Lingfeng Zeng, Bo-Yu Yang, Bing Zhao, Hu Wei, Lin Qu, Dayiheng Liu

arXiv.org

DOI

2026

Unmasking Reasoning Processes: A Process-aware Benchmark for Evaluating Structural Mathematical Reasoning in LLMs

Xiang-Xiang Zheng, Wei-Qi Zhai, Wei Wang, Bo-Yu Yang, Wen-Bo Li, Rui Luo, Hao-Xiang Sun, Yu-Cheng Wang, Zhengze Li, Meng Wang, Yue-Tian Du, Guojie Lin, Ya-Xuan Wang, Xiao-Xiao Xu, Ya-Qi Mo, Xuan Ren, Hu Wei, Bing Zhao

arXiv.org

DOI

2026

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

Zeyu Wang, Xiao-Gang Li, Peiyao Xiao, Qinhao Kong, Benoît Wang, Chen Xu, Zi-Jiang Chen, Bing Zhao, Hu Wei

arXiv.org

DOI

2026

Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs

Longyuan Zhu, Hai-bo Hua, Miao Li, Bing Zhao

arXiv.org

DOI

2026

Beyond Quantity: Trajectory Diversity Scaling for Code Agents

Gu-Hong Chen, Chen Sun, Cheng Fu, Qi-Yao Wang, Zhihong Huang, Chao-Peng Wei, Guang-Xu Chen, Fei-Teng Fang, A. Argha, Bing Zhao, Xander Xu, Qi Han, H. Alinejad-Rokny, Qiang Qu, Bin-Hua Li, Shi-Wen Ni, Min Yang, Hu Wei, Yong-Bin Li

Annual Meeting of the Association for Computational Linguistics

DOI

2026

HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

Wei-Qi Zhai, Zhi-Hai Wang, Jinghan Wang, Bo-Yu Yang, Xiaogang Li, Xander Xu, Bo-Han Wang, Peng Wang, Xingzhe Wu, An-Feng Li, Qi-Yuan Feng, Yu-Hao Zhou, Tao Han, Wen-Jie Luo, Yi-Yuan Li, Xiang Zheng, Y. Wang, Rui Luo, Guojie Lin, Peiyao Xiao, Chen Xu, Benoît Wang, Ze-Yu Wang, Zichao Chen, Jianan Ye, Yi-Jie Hu, Jialong Chen, Zong-Wen Shen, Yuliang Xu, An Yang, Bo-Wen Yu, Dayiheng Liu, Jun-Yang Lin, Hu Wei, Q. Shen, Bing Zhao

arXiv.org

DOI

2026

Human Tool: An MCP-Style Framework for Human-Agent Collaboration

Yuan-Rong Tang, Hui-Ling Peng, Bing Zhao, Hengyang Ding, Hanchao Song, Tianhong Wang, Chen Zhong, Jiangtao Gong

arXiv.org

DOI

2025

StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models

Xiang-Xiang Zhang, Jing-Xuan Wei, Dong-Hong Zhong, Qi Chen, Caijun Jia, Cheng Tan, Jinming Gu, Xiao-Bo Qin, Zhiping Liu, Liang Hu, Tong Sun, Yu-Chen Wu, Zewei Sun, Chenwei Lou, Hua Zheng, Tianyang Zhan, Changbao Wang, Shuangzhi Wu, Zefa Lin, Chang Guo, Si-Hang Yuan, Riwei Chen, Shi-Xiong Zhao, Yingping Zhang, Gaowei Wu, Bi-Hui Yu, Jia-Hui Wu, Zhe-Hui Zhao, Qianqian Liu, Ruo-Feng Tang, Xingyue Huang, Bing Zhao, Mengyang Zhang, Youqiang Zhou

arXiv.org

DOI

2025

LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios

Bing Zhao, Lin Geng Foo, Ping Hu, Christian Theobalt, Hossein Rahmani, Jun Liu

arXiv.org

DOI

2025

Infinite-Instruct: Synthesizing Scaling Code instruction Data with Bidirectional Synthesis and Static Verification

W. Xing, Wenke Lu, Ye-Heng Duan, Bing Zhao, Zhenghui Kang, Yao-Long Wang, Kai Gao, Lei Qiao

arXiv.org

DOI

2025

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Wei-Xun Wang, Xiao-Xiao Xu, Wanhe An, Fangwen Dai, Wei Gao, Yancheng He, Ju Huang, Qiang Ji, Hanqi Jin, Xiaoyang Li, Yang Li, Zhongwen Li, Shi-Rong Lin, Jia-Shun Liu, Zenan Liu, T. Luo, Dilxat Muhtar, Yuan Qu, Jiaqiang Shi, Qing-Hui Sun, Yingshui Tan, Haowen Tang, Run-Ze Wang, Yi Wang, Zhao-Guo Wang, Ya-Nan Wu, Shaopan Xiong, Bin Xu, Xander Xu, Yu-Chi Xu, Qipeng Zhang, Xixia Zhang, Haizhou Zhao, Jie Zhao, Shu-Man Zhao, Bai-xiu Zheng, Jianhui Zheng, Suhang Zheng, Yanni Zhu, Meng-Yao Cai, Ke-Fan Cao, Xi-Tong Chen, Yue Dai, L. Du, Tao Feng, Tao He, Jin Hu, Yi-Jie Hu, Ziyu Jiang, Cheng Li, Xiang Li, Jing Liang, Xin Lin, Chong-Yuan Liu, Liu Zhendong, Zhiqiang Lv, Hao-Tao Mi, Ya-Qi Mo, J. Ni, Shi-Xin Pei, Jing-Lei Shen, Xiaoshuai Song, C. Wang, Chao-Fan Wang, Kang-Yu Wang, Pei Wang, Tao Wang, Wei Wang, Kejun Xiao, Mingyu Xu, Tiange Xu, N. Y.A, Si-Ran Yang, Jia-Yu Ye, Y. Zang, Duo Zhang, Jun-Bo Zhang, Bo Zheng, Wanxi Deng, Ling Pan, Lin Qu, Wen-Bo Su, Jia-Mang Wang, HuanWen Wei, Minggang Wu, Chenghua Yu, Bing Zhao, Zhi-Cheng Zheng, Bo Zheng

arXiv.org

DOI

2025

MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains

Kaiwen Wei, Shan Rui, Dongsheng Zou, Jian-Zhong Yang, Bing Zhao, Jun-Nan Zhu, Jiang Zhong

AAAI Conference on Artificial Intelligence

DOI

2025

FMQS: Enabling Fast Multimedia Data Queries in Edge Storage Systems

Lekang Song, Qiang He, Yanwei Xu, Bing Zhao, Chao Yan, Wenwen Gong, Xiaoxiao Chi, Boyuan Yan, Weiyi Zhong, Rong Jiang

IEEE Transactions on Computational Social Systems

DOI

2025

VTQA: visual tabular data question answering framework based on multi-agent

Yize Fu, Yuhua Liu, Shixian Zhou, Song-Yue Li, Bing Zhao, Yigang Wang, Jing-Fang Mao, Zhi-Guang Zhou

Journal of Vision

DOI

2025

DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making

Tianqi Shang, Weiqing He, C. Zheng, Ling-Yao Li, Li Shen, Bing Zhao

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science

DOI

2023

YUAN 2.0: A Large Language Model with Localized Filtering-based Attention

Shao-Hua Wu, Xu-Dong Zhao, Shenling Wang, Jiangang Luo, Lingjun Li, Xi Chen, Bing Zhao, Wei Wang, Tong Yu, Rongguo Zhang, Jiahua Zhang, Chao Wang

arXiv.org

DOI

2006

基于OpenMaple实现隐函数曲线显示

赵冰

《宁波大学学报(理工版)》

预印本

2026

SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction

Yuanxiang Shi, Jiayi Lin, Xuanyong Lin, Liangcai Su, Yeheng Duan, Wei Wang, Qi Han, Bing Zhao, Wei Hu, Xander Xu, Chenxiong Qian

arXiv preprint

2026

Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks

Xuan Ren, Weiqi Zhai, Tianle Pu, Yihua Zhu, Yihua Zhu, Hu Wei, Bing Zhao

arXiv preprint

2026

REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces

Yuetian Du, Meng Wang, Yucheng Wang, Zhangzhe Chen, Wei Wang, Boyu Yang, Weiqi Zhai, Bing Zhao, Ming Kong, Zhan Zhou, Jie Liu, Qiang Zhu

arXiv preprint

2026

The Illusion of $\textit{What If}$: Evaluating the Breakdown of Counterfactual Reasoning in LLMs

Yucheng Wang, Yuetian Du, Zhengyi Liu, Rongyu Zhang, Bing Zhao, Boyu Yang, Ming Kong, Lin Qu, Hu Wei, Jie Liu, Qiang Zhu

arXiv preprint

2026

RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing

Zijian Kan, Wei Wang, Long Luo, Bing Zhao, Xuan Ren, Weixu Qiao, Wenbo Li, Hu Wei, Lin Qu

arXiv preprint

2026

OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses

Guangzheng Hu, Ziyue Jiang, Weixu Qiao, Lixin Zhang, Jianye Kang, Yuru Wu, Rong Bao, Niantong Li, Wei Wang, Ziyi Cheng, Xinfa Zhu, HangRui Hu, Ting He, Bing Zhao, Lin Qu, Hu Wei, Jin Xu

arXiv preprint

精选作品

期刊论文

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning

Discovering Millions of Interpretable Features with Sparse Autoencoders

Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement

Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis

ClinConsensus: A Consensus-Based Benchmark for Evaluating Chinese Medical LLMs across Difficulty Levels

BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs

PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice

MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning

Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning

DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning

ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

Living-Harness Is an Interactive-Agent Evolver

GSDiffRec: Enhancing Personalized Sequential Recommendation via Diffusion Augmentation and Guidance Optimization

Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction

Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery

Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements

Unmasking Reasoning Processes: A Process-aware Benchmark for Evaluating Structural Mathematical Reasoning in LLMs

FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs

Beyond Quantity: Trajectory Diversity Scaling for Code Agents

HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

Human Tool: An MCP-Style Framework for Human-Agent Collaboration

StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models

LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios

Infinite-Instruct: Synthesizing Scaling Code instruction Data with Bidirectional Synthesis and Static Verification

Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains

FMQS: Enabling Fast Multimedia Data Queries in Edge Storage Systems

VTQA: visual tabular data question answering framework based on multi-agent

DynamiCare: A Dynamic Multi-Agent Framework for Interactive and Open-Ended Medical Decision-Making

YUAN 2.0: A Large Language Model with Localized Filtering-based Attention

基于OpenMaple实现隐函数曲线显示

预印本

SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction

Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks

REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces

The Illusion of $\textit{What If}$: Evaluating the Breakdown of Counterfactual Reasoning in LLMs

RubricRM: Generative Reward Modeling via Dynamic Rubrics for Image Generation and Editing

OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses