Yuxi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuxi Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Nyutian Long
New York University, New York, USA
2 shared publications - Guanzi Yao
Northwestern University, Evanston, USA
1 shared publication - Heyao Liu
Northeastern University, Boston, USA
1 shared publication - Huajun Zhang
Syracuse University, Syracuse, USA
1 shared publication - Ruotong Wang
Rutgers University, Piscataway, USA
1 shared publication - Shunqi Liu
University of Southern California, USA
1 shared publication
Latest Publications
- Open Access
- 20 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 632-639
Retrieval-Augmented Large Language Model Agents for Automated Scientific Literature Review Generation
This study investigates a method that integrates retrieval-augmented mechanisms into large language model agents for scientific literature review generation. The approach addresses the limitations of traditional review models that rely on parametric knowledge with insufficient timeliness and limited coverage. Incorporating external document retrieval and dynamic information fusion into the generation process enhances the accuracy and completeness of the output. The overall framework consists of query encoding, semantic retrieval, document filtering, knowledge fusion, language modeling, task planning, memory storage, and reinforcement optimization, forming a closed loop of retrieval, understanding, and generation. Relevant document fragments are first retrieved through semantic vector search to ensure comprehensive and reliable information sources. These external representations are then integrated with the internal embeddings of the language model through weighted fusion, which preserves fluency while maintaining factual grounding. The task planning module constrains logical flow and text structure, and reinforcement learning optimization further improves relevance and consistency. Comparative experiments on large-scale scientific literature datasets demonstrate that the method outperforms existing approaches on ROUGE, BLEU, METEOR, and diversity metrics, validating its effectiveness and practicality. The findings show that combining retrieval augmentation with agent architectures can significantly improve coverage, accuracy, and language quality in review generation, providing a feasible solution for knowledge organization in complex literature environments.
- 20 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 632-639
Open AccessRetrieval-Augmented Large Language Model Agents for Automated Scientific Literature Review Generation
This study investigates a method that integrates retrieval-augmented mechanisms into large language model agents for scientific literature review generation. The approach addresses the limitations of traditional review models that rely on parametric knowledge with insufficient timeliness and limited coverage. Incorporating external document retrieval and dynamic information fusion into the generation process enhances the accuracy and completeness of the output. The overall framework consists of query encoding, semantic retrieval, document filtering, knowledge fusion, language modeling, task planning, memory storage, and reinforcement optimization, forming a closed loop of retrieval, understanding, and generation. Relevant document fragments are first retrieved through semantic vector search to ensure comprehensive and reliable information sources. These external representations are then integrated with the internal embeddings of the language model through weighted fusion, which preserves fluency while maintaining factual grounding. The task planning module constrains logical flow and text structure, and reinforcement learning optimization further improves relevance and consistency. Comparative experiments on large-scale scientific literature datasets demonstrate that the method outperforms existing approaches on ROUGE, BLEU, METEOR, and diversity metrics, validating its effectiveness and practicality. The findings show that combining retrieval augmentation with agent architectures can significantly improve coverage, accuracy, and language quality in review generation, providing a feasible solution for knowledge organization in complex literature environments.
- Open Access
- 29 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 585-592
Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks
This paper proposes a topology-aware graph reinforcement learning approach to address the routing policy optimization problem in cloud server environments. The method builds a unified framework for state representation and structural evolution by integrating a Structure-Aware State Encoding (SASE) module and a Policy-Adaptive Graph Update (PAGU) mechanism. It aims to tackle the challenges of decision instability and insufficient structural awareness under dynamic topologies. The SASE module models node states through multi-layer graph convolution and structural positional embeddings, capturing high-order dependencies in the communication topology and enhancing the expressiveness of state representations. The PAGU module adjusts the graph structure based on policy behavior shifts and reward feedback, enabling adaptive structural updates in dynamic environments. Experiments are conducted on the real-world GEANT topology dataset, where the model is systematically evaluated against several representative baselines in terms of throughput, latency control, and link balance. Additional experiments, including hyperparameter sensitivity, graph sparsity perturbation, and node feature dimensionality variation, further explore the impact of structure modeling and graph updates on model stability and decision quality. Results show that the proposed method outperforms existing graph reinforcement learning models across multiple performance metrics, achieving efficient and robust routing in dynamic and complex cloud networks.
- 29 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 585-592
Open AccessTopology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks
This paper proposes a topology-aware graph reinforcement learning approach to address the routing policy optimization problem in cloud server environments. The method builds a unified framework for state representation and structural evolution by integrating a Structure-Aware State Encoding (SASE) module and a Policy-Adaptive Graph Update (PAGU) mechanism. It aims to tackle the challenges of decision instability and insufficient structural awareness under dynamic topologies. The SASE module models node states through multi-layer graph convolution and structural positional embeddings, capturing high-order dependencies in the communication topology and enhancing the expressiveness of state representations. The PAGU module adjusts the graph structure based on policy behavior shifts and reward feedback, enabling adaptive structural updates in dynamic environments. Experiments are conducted on the real-world GEANT topology dataset, where the model is systematically evaluated against several representative baselines in terms of throughput, latency control, and link balance. Additional experiments, including hyperparameter sensitivity, graph sparsity perturbation, and node feature dimensionality variation, further explore the impact of structure modeling and graph updates on model stability and decision quality. Results show that the proposed method outperforms existing graph reinforcement learning models across multiple performance metrics, achieving efficient and robust routing in dynamic and complex cloud networks.