Mingyue Cheng

Mingyue Cheng  程明月

Ph.D  ·  Associate Researcher
State Key Laboratory of Cognitive Intelligence
School of Computer Science and Technology,  University of Science and Technology of China
USTC-AGI Group Google Scholar GitHub
Email: mycheng@ustc.edu.cn
Address: B709, Xinzhi Building, Gaoxin Campus of USTC, Hefei, Anhui, China, 230031

Biography

I am an Associate Researcher at the School of Computer Science and Technology, University of Science and Technology of China (USTC). I am also affiliated with the State Key Laboratory of Cognitive Intelligence at USTC, working under the guidance of Prof. Enhong Chen and Prof. Qi Liu. Previously, I obtained my Ph.D. degree under the supervision of Prof. Qi Liu.

Research Interests

My research develops cognitive intelligence methods for complex data mining, centered on LLMs and Agentic AI, and driven by the dual foundations of time-series observations and scientific knowledge. My methodological focus lies in context representation and reasoning, aiming to build predictive intelligence for complex systems through multimodal semantic understanding, slow-thinking temporal reasoning, and autonomous agentic interaction.

Broader Application and Evaluation Scenarios

AI for Science

Applying LLMs and Agentic AI to structured scientific data modeling, scientific literature mining, and evidence-grounded discovery.

AI for Energy Systems

Building context-aware forecasting agents for load, solar, and wind systems, renewable analytics, grid balancing, and risk-aware operation.

AI for User Modeling

Modeling behavioral sequences and preference dynamics for explainable recommendation, user simulation, and interactive decision support.

Research collections: 🤖 LLMs and Agentic AI · 📊 Time Series Analysis · 🧮 Tabular Data Mining · 📚 AI for Science
欢迎脚踏实地而又积极主动的本科生、研究生同学加入认知智能全国重点实验室 USTC-AGI Group。

Latest News

View All News →

Selected Publications

(* Corresponding Author, + Equal Contribution)

📘 Preprint

  1. Mingyue Cheng, Xiaoyu Tao, Qi Liu, Ze Guo, Enhong Chen, Position: Beyond Model-Centric Prediction — Agentic Time Series Forecasting. (Preprint) [PDF]
  2. Xiaohan Zhang, Tian Gao, Mingyue Cheng*, Bokai Pan, Ze Guo, Yaguo Liu, Xiaoyu Tao, Qi Liu, AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting. (Preprint) [PDF] [Code]
  3. Bokai Pan, Mingyue Cheng*, Zhiding Liu, Shuo Yu, Xiaoyu Tao, Yuchong Wu, Qi Liu, Defu Lian, Enhong Chen, CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting. (Preprint) [PDF] [Code]
  4. Xiaoyu Tao, Mingyue Cheng, Chuang Jiang, Tian Gao, Huanjian Zhang, Yaguo Liu, Qi Liu, Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting. (Preprint) [PDF] [Code]
  5. Yitong Zhou, Yucong Luo, Mingyue Cheng*, Jiahao Wang, Daoyu Wang, Tingyue Pan, Jintao Zhang, Qi Liu, Enhong Chen, Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs. (Preprint) [PDF] [Code]
  6. Daoyu Wang, Qingchuan Li, Mingyue Cheng, Jie Ouyang, Shuo Yu, Qi Liu, Enhong Chen, StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning. (Preprint) [PDF]
  7. Tingyue Pan, Jie Ouyang, Mingyue Cheng, Qingchuan Li, Zirui Liu, Daoyu Wang, Mingfan Pan, Shuo Yu, Qi Liu, PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization. (Preprint) [PDF]
  8. Daoyu Wang, Mingyue Cheng*, Shuo Yu, Zirui Liu, Ze Guo, Xin Li, Qi Liu, PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature. (Preprint) [PDF] [Code]

📘 Released Survey

  1. Mingyue Cheng, Daoyu Wang, Shuo Yu, Qingchuan Li, Jie Ouyang, Yucong Luo, Yiju Zhang, Qi Liu*, Enhong Chen, A Comprehensive Survey of the LLM-Based Agent: The Contextual Cognition Perspective. (Preprint) [Preprint]
  2. Mingyue Cheng, Zhiding Liu, Xiaoyu Tao, Qi Liu*, Jintao Zhang, Tingyue Pan, Shilong Zhang, Panjing He, Xiaohan Zhang, Daoyu Wang, Jiahao Wang, Enhong Chen, A Comprehensive Survey of Time Series Forecasting: Concepts, Challenges, and Future Directions. (Preprint) [PDF] [Code]
  3. Mingyue Cheng, Qingyang Mao, Qi Liu*, Yitong Zhou, Yupeng Li, Jiahao Wang, Jiaying Lin, Jiawei Cao, Enhong Chen, A Survey on Table Mining with Large Language Models: Challenges, Advancements and Prospects. (Preprint) [PDF] [Code]

🐎 Year of the Fire Horse (Bing Wu Year, 2026)

  1. Mingyue Cheng, Yucong Luo, Jie Ouyang, Qi Liu*, Huijie Liu, Li Li, Shuo Yu, Bohou Zhang, Jiawei Cao, Jie Ma, Daoyu Wang, Enhong Chen, A Survey on Knowledge-Oriented Retrieval-Augmented Generation. ACM Transactions on Information Systems (ACM TOIS) Accepted. [PDF] [Code]
  2. Mingyue Cheng, Xiaoyu Tao, Huajian Zhang, Qi Liu*, Enhong Chen, InstructTime++: Time Series Classification with Multimodal Language Modeling via Implicit Feature Enhancement. ACM Transactions on Intelligent Systems and Technology (ACM TIST) Accepted. [PDF] [Code]
  3. Yitong Zhou, Mingyue Cheng*, Qingyang Mao, Yucong Luo, Qi Liu, Yupeng Li, Xiaohan Zhang, Deguang Liu, Xin Li, Enhong Chen, Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables. KDD2026 Accepted. [PDF] [Code]
  4. Xiaoyu Tao, Mingyue Cheng*, Ze Guo, Shuo Yu, Yaguo Liu, Qi Liu, Shijin Wang, MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning. ICML2026 Accepted. [PDF]
  5. Mingyue Cheng, Yaguo Liu, Daoyu Wang, Xiaoyu Tao, Qi Liu*, CoGenCast: A Coupled Autoregressive-Flow Generative Framework for Time Series Forecasting. ICML2026 Accepted. [PDF]
  6. Xiaoyu Tao, Shilong Zhang, Mingyue Cheng*, Daoyu Wang, Tingyue Pan, Bokai Pan, Changqing Zhang, Shijin Wang, From Values to Tokens: An LLM-Driven Framework for Context-aware Time Series Forecasting via Symbolic Discretization. IJCAI2026 Accepted. [PDF]
  7. Bohou Zhang, Xiaoyu Tao, Mingyue Cheng*, Huijie Liu, Qi Liu, ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement. IJCAI2026 Accepted.
  8. Jiawei Cao, Jie Ouyang, Mingyue Cheng*, Zhaomeng Zhou, Chunli Liu, Yupeng Li, Zirui Liu, Shijin Wang, Re3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination. ACL2026 Accepted.
  9. Huajian Zhang, Mingyue Cheng*, Yucong Luo, Xiaoyu Tao, STaR: Towards Cognitive Table Reasoning via Slow-Thinking Large Language Models. ACM WWW2026. [PDF] [Code]
  10. Zhiding Liu, Ben Chen, Mingyue Cheng*, Enhong Chen, Li Li, Chenyi Lei*, Wenwu Ou, Han Li and Kun Gai, Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce. ACM WWW2026. [PDF]
  11. Shuo Yu, Mingyue Cheng*, Daoyu Wang, Qi Liu, Zirui Liu, Ze Guo, Xiaoyu Tao, MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation. ACM WWW2026. [PDF]
  12. Mingyue Cheng, Jiahao Wang, Daoyu Wang, Xiaoyu Tao, Qi Liu*, Enhong Chen, Can Slow-Thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting. ACM WSDM2026: 99–110, Feb 2026. [PDF] [Code]
  13. Mingyue Cheng, Xiaoyu Tao, Zhiding Liu, Qi Liu*, Hao Zhang, Rujiao Zhang and Enhong Chen, TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders, ACM WSDM2026: 498–508, Feb 2026. [arXiv version] [Code]
  14. Chuang Jiang, Mingyue Cheng*, Xiaoyu Tao, Qingyang Mao, Jie Ouyang and Qi Liu, TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning. ACM WSDM2026: 260–270, Feb 2026. [PDF] [Code]
  15. Qingchuan Li, Mingyue Cheng*, Zirui Liu, Daoyu Wang, Yuting Zeng, Tongxuan Liu, From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation. AAAI2026: 31671–31679, Mar 2026. [PDF] [DOI]
  16. Yupeng Li, Mingyue Cheng*, Yucong Luo, Yitong Zhou, Qingyang Mao, Shijin Wang, BLADE: A Behavior-Level Data Augmentation Framework with Dual Fusion Modeling for Multi-Behavior Sequential Recommendation. AAAI2026: 15189–15197, Mar 2026. [PDF] [DOI]

🐍 Year of the Wood Snake (Yi Si Year, 2025)

  1. Mingyue Cheng, Jiqian Yang, Tingyue Pan, Qi Liu*, Zhi Li, ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis, ACM WWW2025, Sydney, 2025. [PDF] [Code] — Included in sktime
  2. Xiaoyu Tao, Tingyue Pan, Mingyue Cheng*, Yucong Luo, Qi Liu, Enhong Chen, Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification. (ACM Transactions on Intelligent Systems and Technology (ACM TIST)) [PDF] [Code]
  3. Mingyue Cheng, Yiheng Chen, Qi Liu*, Zhiding Liu, Yucong Luo, Enhong Chen, InstrucTime: Advancing Time Series Classification with Multimodal Language Modeling, ACM WSDM2025 (Best of WSDM): 792–800, Hannover, 2025. [PDF] [Code] [Poster]
  4. Mingyue Cheng, Xiaoyu Tao, Qi Liu*, Hao Zhang, Yiheng Chen, Defu Lian, Cross-Domain Pre-training with Language Models for Transferable Time Series Representations, ACM WSDM2025: 175–183, Hannover, 2025. [PDF] [Code] [Poster]
  5. Daoyu Wang, Mingyue Cheng*, Zhiding Liu, Qi Liu, TimeDART: A Diffusion Autoregressive Transformer for Self-supervised Time Series Representation, ICML 2025, Vancouver, PMLR 267, 2025. [PDF] [Code]
  6. Jie Ouyang, Tingyue Pan, Mingyue Cheng*, Ruiran Yan, Yucong Luo, Jiaying Lin, Qi Liu, HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on RAG, ACL 2025: 6036–6063, Vienna, 2025. [PDF] [Code]
  7. Mingyue Cheng, Jintao Zhang, Zhiding Liu, Chunli Liu*, A Hybrid Multi-Factor Framework for Dynamic Intraoperative Hypotension Prediction, IJCAI 2025: 4923–4931, Montreal, 2025. [PDF]
  8. Jintao Zhang, Mingyue Cheng*, Xiaoyu Tao, Zhiding Liu, Daoyu Wang, Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecasting, IJCAI 2025: 6993–7001, Montreal, 2025. [PDF] [Code]
  9. Yitong Zhou, Mingyue Cheng*, Qingyang Mao, Feiyang Xu, Xin Li, Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner, IJCAI 2025: 2503–2511, Montreal, 2025. [PDF] [Code]
  10. Hao Zhang, Mingyue Cheng*, Qi Liu, Zhiding Liu, Linbo Zhu, Yu Su, Towards Automatic Sampling of User Behaviors for Sequential Recommender Systems, IJCAI 2025: 3624–3632, Montreal, 2025. [PDF] [Code]
  11. Jiahao Wang, Mingyue Cheng*, Qingyang Mao, Qi Liu, Feiyang Xu, Xin Li, Enhong Chen, TableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via LLMs, ACM CIKM 2025. [PDF] [Code]
  12. Shuo Yu, Mingyue Cheng*, Jiqian Yang, Jie Ouyang, et al., Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study, ACM CIKM 2025.

🐉 Year of the Wood Dragon (Jia Chen Year, 2024)

  1. Jie Ouyang, Yucong Luo, Mingyue Cheng*, Shuo Yu, Daoyu Wang, Qi Liu, Enhong Chen, Revisiting the Solution of Meta KDD Cup 2024: CRAG. (KDD Cup Workshop, 2nd Place in Task 2 & Task 3) [Slides] [Poster]
  2. Mingyue Cheng, Qi Liu*, Wenyu Zhang, Zhiding Liu, Hongke Zhao, Enhong Chen, A General Tail Item Representation Enhancement Framework for Sequential Recommender Systems, Frontiers of Computer Science (FCS), 2024, 18(6): 1–12. [PDF] [Code]
  3. Rujiao Zhang, Hao Zhang, Yucong Luo, Zhiding Liu, Mingyue Cheng, Qi Liu, Enhong Chen*, Learning the Dynamics in Sequential Recommendation by Exploiting Real-time Information, ACM CIKM2024: 4288–4292, Oct 2024. [PDF]
  4. Jie Wang, Fajie Yuan, Mingyue Cheng, et al., TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback, APWeb-WAIM2024: 193–208, Aug 2024. [PDF]
  5. Zhiding Liu, Jiqian Yang, Mingyue Cheng*, Yucong Luo, Zhi Li, Generative Pretrained Hierarchical Transformer for Time Series Forecasting, ACM SIGKDD2024: 2003–2013, Barcelona, 2024. [PDF]
  6. Yucong Luo, Mingyue Cheng, Hao Zhang, Junyu Lu, Enhong Chen*, Unlocking the Potential of Large Language Models for Explainable Recommendations. (DASFAA2024) [PDF] [Code]
  7. Junzhe Jiang, Shang Qu, Mingyue Cheng*, Qi Liu, et al., Reformulating Sequential Recommendation: Learning Dynamic User Interest with Content-enriched Language Modeling. (DASFAA2024) [PDF] [Code]
  8. Mingyue Cheng, Hao Zhang, Qi Liu*, Fajie Yuan, Zhi Li, Zhenya Huang, Enhong Chen, Longfei Li, Jun Zhou, Empowering Sequential Recommender Systems from Mixture of Collaborative Signals and Semantic Relatedness. (DASFAA2024) [PDF] [Code]
  9. Hao Zhang, Mingyue Cheng*, Qi Liu, Yucong Luo, Rui Li, Enhong Chen, Learning Recommender Systems with Soft Target: A Decoupled Perspective. DASFAA 2024, LNCS 14852, Gifu, Japan, 2024. [PDF] [Code]
  10. Mingyue Cheng, Hao Zhang, Jiqian Yang, Qi Liu*, Li Li, Xin Huang, Liwei Song, Zhi Li, Zhenya Huang, Enhong Chen, Towards Personalized Evaluation of Large Language Models with An Anonymous Crowd-Sourcing Platform. (WWW2024)
  11. Junchen Fu, Fajie Yuan, Yu Song, Zheng Yuan, Mingyue Cheng, et al., Exploring Adapter-based Transfer Learning for Recommender Systems, ACM WSDM'2024: 208–217, Mar 2024. [PDF] [Code]

📘 2023 and Before

  1. Zhiding Liu, Mingyue Cheng, Zhi Li, Zhenya Huang, Qi Liu, Yanhu Xie, Enhong Chen, Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective, NeurIPS'2023: 36, New Orleans, 2023. [PDF] [Code]
  2. 耿杰, 刘春丽*, 魏雪梅, 程明月, 袁昆, 李洋, 刘业政, 基于用户重购行为的产品推荐方法, 计算机研究与发展 2023, 60(8): 1795–1807.
  3. Mingyue Cheng, Qi Liu*, Zhiding Liu, Zhi Li, Yucong Luo, Enhong Chen, FormerTime: Hierarchical Multi-scale Representation for Multivariate Time Series Classification, ACM WWW'2023: 1437–1445, Austin, 2023. [PDF] [Code]
  4. Wenqiang He, Mingyue Cheng, Qi Liu*, Zhi Li, ShapeWordNet: An Interpretable Shapelet Neural Network for Physiological Signal Classification, DASFAA'2023: 353–369, Tianjin, 2023.
  5. Mingyue Cheng, Zhiding Liu+, Qi Liu*, Shenyang Ge, Enhong Chen, Towards Automatic Designing of Deep Hybrid Network Architecture for Sequential Recommendation, ACM WWW'2022: 1923–1932. [Code]
  6. Zhiding Liu, Mingyue Cheng, Zhi Li, Qi Liu, Enhong Chen*, One Person, One Model — Learning Compound Router for Sequential Recommendation, IEEE ICDM'2022. [Code]
  7. Junzhe Jiang, Mingyue Cheng, Qi Liu*, Zhi Li, Enhong Chen, Nested Named Entity Recognition from Medical Texts: A Multi-task Learning Approach, CAAI CICAI'2022: 248–259.
  8. Runlong Yu, Qi Liu*, Yuyang Ye, Mingyue Cheng, Enhong Chen, Jianhui Ma, Collaborative List-and-Pairwise Filtering from Implicit Feedback, IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE), 2022, 34(6): 2667–2680.
  9. Kai Zhang, Qi Liu*, Zhenya Huang, Mingyue Cheng, Kun Zhang, Mengdi Zhang, Wei Wu, Enhong Chen, Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification, ACM SIGIR'2022: 1566–1576.
  10. Mingyue Cheng, Fajie Yuan+, Qi Liu*, Xin Xin, Enhong Chen, Learning Transferrable User Representations with Sequential Behaviors via Contrastive Pre-training, IEEE ICDM'2021: 51–60.
  11. Mingyue Cheng, Fajie Yuan+, Qi Liu*, Shenyang Ge, Zhi Li, Runlong Yu, Defu Lian, Senchao Yuan, Enhong Chen, Learning Recommender Systems with Implicit Feedback via Soft Target Enhancement, ACM SIGIR'2021: 575–584.
  12. Linan Yue, Qi Liu*, Han Wu, Kai Zhang, Yanqing An, Mingyue Cheng, Biao Yin, Dayong Wu, NeurJudge: A Circumstance-aware Neural Framework for Legal Judgment Prediction, ACM SIGIR'2021: 973–982.
  13. Yanqing An, Qi Liu*, Han Wu, Kai Zhang, Linan Yue, Mingyue Cheng, Hongke Zhao, Senchao Yuan, Enhong Chen, LawyerPAN: A Proficiency Assessment Network for Trial Lawyers, ACM SIGKDD'2021: 5–13.
  14. Mingyue Cheng, Runlong Yu, Qi Liu*, Hongke Zhao, Hefu Zhang, Enhong Chen, Alpha-Beta Sampling for Pairwise Ranking in One-Class Collaborative Filtering, IEEE ICDM'2019: 1000–1005.
  15. 程明月, 刘淇*, 李徵, 于润龙, 高维博, 陈恩红, 多重对级贝叶斯个性化排序算法. (南京信息工程大学学报自然科学版, 2019(03): 302–308)

Open Source

CastClaw（观星阁）
2026.04 GitHub Website Docs ⭐ 45
CastClaw（观星阁） is an open-source framework for agentic time series forecasting. It enables LLM agents to autonomously perform data analysis, model selection, feature engineering, and iterative forecasting refinement through structured tool-augmented workflows. CastClaw（观星阁） bridges classical time series methods with agentic reasoning, supporting diverse forecasting scenarios ranging from short-term point prediction to long-horizon multi-step forecasting, with built-in evaluation and interpretability mechanisms.
CastFactory（炼星坊）
2026.05 GitHub Website ⭐ 3
CastFactory（炼星坊） is an open-source framework for LLM-driven time series forecasting model training, designed to make it extremely easy for users to build and adapt TSF models with modern large-model pipelines. It provides a unified and practical workflow for continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL), helping researchers and practitioners develop, optimize, and evaluate LLM-based forecasting systems with much lower engineering overhead.
FutureCast（天星台）
2026.05 GitHub Website ⭐ 2
FutureCast（天星台） is a unified evaluation suite for time series models and agentic forecasting systems. It organizes benchmark management, metric computation, error attribution, and report generation into a consistent evaluation workflow, helping researchers compare model capabilities and system-level gains across datasets, scenarios, and task settings including forecasting, classification, and anomaly detection.
NeoResearch（智多星）
2026.05 Website
NeoResearch（智多星） is an autonomous research agent system for time series forecasting model development. It connects research hypothesis generation, candidate recipe search, controlled experiments, evaluation diagnosis, and research memory into a reproducible loop, supporting systematic iteration from problem definition to validated forecasting model candidates.
Academic Search
2026.04 GitHub ⭐ 436
Academic Search is an open-source academic literature research skill for Claude Code. It unifies paper discovery across arXiv, Semantic Scholar, Google Scholar, CNKI, and other scholarly sources, while supporting query expansion, citation tracing, BibTeX export, PDF-first retrieval, and multi-source deduplication. With recency-aware ranking and browser-assisted fallback for hard-to-access platforms, it helps researchers surface recent, high-value papers and their code resources more efficiently.
PaperScout
2026.01 GitHub Website Paper ⭐ 5
PaperScout is an autonomous academic paper search agent trained with Process-Aware Sequence-Level Policy Optimization (PSPO). It formulates literature search as a multi-turn sequential decision-making problem, allowing agents to dynamically decide when to Search for new directions and when to Expand along citation and related-paper paths. PaperScout turns scholarly retrieval into an agentic RL environment for learning efficient tool-use policies and producing stronger recall under realistic research queries.
TabClaw
2026.03 GitHub Website Platform ⭐ 58
TabClaw is an open-source agentic framework that empowers LLMs to reason over complex, real-world tabular data. It decomposes table-centric tasks into structured sub-goals, equips agents with code execution, schema-aware lookup, and formula tools, and coordinates them through multi-step decision workflows. TabClaw is designed to tackle challenges beyond flat QA — including multi-hop joins, conditional aggregation, and cross-table inference — making it suitable for enterprise data analysis and scientific table understanding.
Claw-R1
2026.03 GitHub Website ⭐ 192
Claw-R1 is an open-source framework for training reasoning-intensive, tool-using LLM agents via reinforcement learning. It extends standard RL environments with agentic action spaces — including tool invocation, multi-turn interaction, and environment feedback — and supports GRPO-based policy optimization with customizable reward signals. Designed for reproducibility and extensibility, Claw-R1 enables researchers to study how RL shapes emergent reasoning behaviors, tool-use strategies, and decision robustness in large language models.
Agent-R1
2025.04 GitHub Website Docs ⭐ 1520
Agent-R1 is a large-model agent training framework for end-to-end reinforcement learning fine-tuning. It supports GRPO-based policy optimization with reward signals derived from environment feedback, and equips agents with multi-tool orchestration, persistent long-term memory, and reflective self-correction across interaction turns. Grounded in the DeepSeek-R1 paradigm, Agent-R1 enables researchers to train LLM agents that not only reason under uncertainty but also learn to use tools strategically and recover from failures autonomously.

Benchmarks & Datasets

E-Commerce Search · Recall to Relevance
KuaiSearch Search-based Recommendation Paper
2026.02 Website GitHub ⭐ 18
KuaiSearch: A Large-Scale E-Commerce Search Dataset for Recall, Ranking, and Relevance is built from real user search interactions on Kuaishou. It preserves authentic user queries and natural-language product texts, covers cold-start users and long-tail products, and spans the three key stages of modern search systems: recall, ranking, and relevance judgment.
Scientific Literature · Agentic Evaluation
PaperArena Scientific Literature Mining Paper
2025.10 Website GitHub ⭐ 17
PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literature benchmarks agentic systems on scientific reading and reasoning with tool use. It targets literature understanding, tool-augmented reasoning, and evidence-grounded evaluation over scientific papers and related scholarly workflows.
AI for Science · Chemical Tables
ChemTable Scientific Literature Mining Paper
2025.06 GitHub ⭐ 6
Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables introduces ChemTable, a real-world benchmark curated from chemical literature. It supports two core tasks: table recognition and table understanding, with expert annotations over cell polygons, logical layouts, and chemistry-specific semantic labels such as reagents, catalysts, yields, and graphical components.
RAG Evaluation · Dynamic Benchmark
HoH Retrieval-Augmented Generation Paper
2025.06 GitHub ⭐ 6
HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on RAG studies how retrieval-augmented generation systems fail when knowledge becomes stale. It provides a dynamic evaluation setting for measuring temporal robustness, outdated-information sensitivity, and the impact of knowledge freshness in modern RAG pipelines.

Education

Working Experiences

Teaching

Honors and Awards

Professional Service

Program Committee Member
  • AAAI Conference on Artificial Intelligence (AAAI): 2026, 2027
  • ACM International World Wide Web Conference (TheWebConf): 2024, 2025, 2026
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD): 2023, 2024, 2025, 2026, 2027
  • ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL): 2026
  • International Conference on Learning Representations (ICLR): 2025
  • International Conference on Machine Learning (ICML): 2025, 2026
  • Conference on Neural Information Processing Systems (NeurIPS): 2024, 2025, 2026
  • Annual Meeting of the Association for Computational Linguistics (ACL): 2025, 2026
  • International Joint Conference on Artificial Intelligence (IJCAI): 2024, 2025, 2026 (SPC)
  • International Conference on Web Search and Data Mining (WSDM): 2025
  • SIAM International Conference on Data Mining (SDM): 2024
  • ACM International Conference on Information and Knowledge Management (CIKM): 2024, 2025
  • Database Systems for Advanced Applications (DASFAA): 2024, 2025
  • IEEE Task Force on AI for Time Series and Spatio-Temporal Data
Journal Reviewer
  • IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE)
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Neural Network and Learning Systems (IEEE TNNLS)
  • IEEE Transactions on Industrial Informatics (IEEE TII)
  • IEEE Transactions on Audio, Speech and Language Processing (IEEE T-ASL)
  • ACM Transactions on Knowledge Discovery from Data (TKDD)
  • ACM Transactions on Intelligent Systems and Technology (TIST)
  • Transactions on Machine Learning Research (TMLR)
  • Neurocomputing
  • Frontiers of Computer Science (FCS)
  • 软件学报
  • 计算机学报

Research Grants

Related Links

Prof. Qi Liu
University of Science and Technology of China
USTC
Prof. Enhong Chen
University of Science and Technology of China
USTC
Prof. Fajie Yuan
Westlake University
WU
Prof. Hongke Zhao
Tianjin University
TJU