Daoyu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Daoyu Wang has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Mingyue Cheng
University of Science and Technology of China
10 shared publications - Qi Liu
University of Science and Technology of China
10 shared publications - Enhong Chen
University of Science and Technology of China
7 shared publications - Shuo Yu
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
6 shared publications - Xiaoyu Tao
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
6 shared publications - Yitong Zhou
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China
4 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (12) , 7853-7872
A Comprehensive Survey of Time Series Forecasting: Concepts, Challenges, and Future Directions
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (12) , 7853-7872
A Comprehensive Survey of Time Series Forecasting: Concepts, Challenges, and Future Directions
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 671-682
Mind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agent
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 671-682
Open AccessMind2Report: Expert-Level Commercial Report Synthesis via Cognitive Deep Research Agent
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9097-9101
TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9097-9101
Open AccessTabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9092-9096
Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning
LLM agents increasingly rely on reinforcement learning to improve multi-turn reasoning, tool use, and environment interaction. However, existing training pipelines often treat an agent trajectory as a flat token sequence or a reconstructed message trace, making it difficult to preserve rollout fidelity, manage long contexts, and inspect step-level credit signals. We present Agent-R1, an open-source modular framework for agentic reinforcement learning (RL). Agent-R1 uses interaction steps as the native unit for trajectory representation, replay, and environment interaction, and decouples exact trajectory storage from flexible context construction. The system supports context-management policies, step-level rollout inspection, action-mask visualization, tool-feedback analysis, and unified comparison of related RL algorithms. Through demonstrations on multiple tasks, Agent-R1 enables users to configure, train, inspect, and compare agentic RL workflows within a single interactive interface. Code and project resources are available at https://github.com/AgentR1/Agent-R1.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 9092-9096
Open AccessAgent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning
LLM agents increasingly rely on reinforcement learning to improve multi-turn reasoning, tool use, and environment interaction. However, existing training pipelines often treat an agent trajectory as a flat token sequence or a reconstructed message trace, making it difficult to preserve rollout fidelity, manage long contexts, and inspect step-level credit signals. We present Agent-R1, an open-source modular framework for agentic reinforcement learning (RL). Agent-R1 uses interaction steps as the native unit for trajectory representation, replay, and environment interaction, and decouples exact trajectory storage from flexible context construction. The system supports context-management policies, step-level rollout inspection, action-mask visualization, tool-feedback analysis, and unified comparison of related RL algorithms. Through demonstrations on multiple tasks, Agent-R1 enables users to configure, train, inspect, and compare agentic RL workflows within a single interactive interface. Code and project resources are available at https://github.com/AgentR1/Agent-R1.
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6667-6678
Time Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6667-6678
Open AccessTime Series Forecasting via Reasoning: A Slow-Thinking Approach with Reinforcement Fine-Tuned LLMs
- Open Access
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-57
A Survey on Knowledge-Oriented Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the two. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge, and the challenges associated with aligning retrieved information with generative objectives. We also present a taxonomy that categorizes RAG methods, ranging from basic retrieval-augmented approaches to more advanced models incorporating multimodal data and reasoning capabilities. Additionally, we review the evaluation benchmarks and datasets commonly used to assess RAG systems, along with a detailed exploration of its applications in fields such as question answering, summarization, and information retrieval. Finally, we highlight emerging research directions and opportunities for improving RAG systems, such as enhanced retrieval efficiency, model interpretability, and domain-specific adaptations. This article concludes by outlining the prospects for RAG in addressing real-world challenges and its potential to drive further advancements in natural language processing ( https://github.com/USTCAGI/Awesome-Papers-Retrieval-Augmented-Generation ).
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (8) , 1-57
Open AccessA Survey on Knowledge-Oriented Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has gained significant attention in recent years for its potential to enhance natural language understanding and generation by combining large-scale retrieval systems with generative models. RAG leverages external knowledge sources, such as documents, databases, or structured data, to improve model performance and generate more accurate and contextually relevant outputs. This survey aims to provide a comprehensive overview of RAG by examining its fundamental components, including retrieval mechanisms, generation processes, and the integration between the two. We discuss the key characteristics of RAG, such as its ability to augment generative models with dynamic external knowledge, and the challenges associated with aligning retrieved information with generative objectives. We also present a taxonomy that categorizes RAG methods, ranging from basic retrieval-augmented approaches to more advanced models incorporating multimodal data and reasoning capabilities. Additionally, we review the evaluation benchmarks and datasets commonly used to assess RAG systems, along with a detailed exploration of its applications in fields such as question answering, summarization, and information retrieval. Finally, we highlight emerging research directions and opportunities for improving RAG systems, such as enhanced retrieval efficiency, model interpretability, and domain-specific adaptations. This article concludes by outlining the prospects for RAG in addressing real-world challenges and its potential to drive further advancements in natural language processing ( https://github.com/USTCAGI/Awesome-Papers-Retrieval-Augmented-Generation ).
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6920-6931
MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6920-6931
Open AccessMemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation
- Top Cited PapersOpen Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 99-110
Can Slow-Thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 99-110
Top Cited PapersOpen AccessCan Slow-Thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3009-3019
TableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3009-3019
Open AccessTableTime: Reformulating Time Series Classification as Training-Free Table Understanding with Large Language Models
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3931-3941
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 3931-3941
Open AccessMulti-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study