ADMIRE 课题组

Progressive Subexpression Reuse in Symbolic Regression: Insights from RL-based Search and a Genetic Programming Realization

Xiangdong Wu, Wenjun Wu, Bingrun Chen, Junle Wang, Zhaoxin Fan, Haoyi Zhou, Pengju Zhang, Rongye Shi

RGP 通过子表达式池与引导式种群初始化，在遗传编程中实现渐进式结构复用，支持可解释数学表达式发现。

UrbanNav: Learning Language-Guided Embodied Urban Navigation from Web-Scale Human Trajectories

Yanghong Mei, Yirong Yang, Longteng Guo, Qunbo Wang, Ming-Ming Yu, Xingjian He, Wenjun Wu, Jing Liu

具身智能、城市导航、语言引导导航

TAS-DAQ: Task-Adaptive Sparse Prediction with Dense Query Auxiliary Supervisory for Efficient 3D Object Detection

Yirong Yang, Li Song, Qunbo Wang, Longteng Guo, Ruyi Ji, Mingming Yu, Wenjun Wu, Jing Liu

3D 目标检测、稀疏预测、多模态感知

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World

MingMing Yu, Fei Zhu, Wenzhuo Liu, Yirong Yang, Qunbo Wang, wenjun wu, Jing Liu

具身智能、开放世界导航、持续学习

Soft Knowledge Prompt: Help External Knowledge Become a Better Teacher to Instruct LLM in Knowledge-based VQA

Qunbo Wang, Ruyi Ji, Tianhao Peng, Wenjun Wu, Zechao Li, Jing Liu

多模态问答、知识增强、LLM

GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy

Tianhao Peng, Wenjun Wu, Haitao Yuan, Zhifeng Bao, Zhao Pengru, Xin Yu, Xuetao Lin, Yu Liang et al.

图神经网络、强化学习、异质图学习

Leveraging Partial Symmetry for Multi-Agent Reinforcement Learning

Xin Yu, Rongye Shi, Pu Feng, Yongkai Tian, Simin Li, Shuhao Liao, Wenjun Wu

多智能体强化学习、对称先验、群体智能

Deep Bayesian Active Learning for Learning to Rank: A Case Study in Answer Selection (Extended Abstract)

Qunbo Wang, Wenjun Wu, Yuxing Qi, Yongchi Zhao

主动学习、排序学习、答案选择

CLGT: A Graph Transformer for Student Performance Prediction in Collaborative Learning

Tianhao Peng, Yu Liang, Wenjun Wu, Jian Ren, Zhao Pengrui, Yanjun Pu

教育数据挖掘、协作学习、图 Transformer

MemOcc: Hierarchical Memory for Indoor Continuous Occupancy Mapping

具身智能、连续占据建图、层次记忆

Agents Trainer: Automatically Training Multi-Agent Reinforcement Learning Models for Drone Swarm Using Language Model-Based Agents

Jiabin Lou

大模型智能体、多智能体强化学习、无人机群体

REMIX: Reusable Experience Memory for Adaptive Web Service Composition

用可复用经验记忆支持服务组合智能体适应任务与运行环境变化。

FLARE: Causal Fault Localization and Minimal Repair for Web Service Composition with LLM Agents

以 LLM 智能体完成服务组合中的因果故障定位，并生成尽可能小的修复方案。

TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices

Junle Wang, Ruibo Chen, Yuanshuai Wang, Xingchuang Liao, Zhimin Fan, Xiangdong Wu, Wenjun Wu, Xuehong Liu et al.

融合调用拓扑和多模态信号，通过多智能体协作与持续演化定位微服务根因。

STAR: A Stage-attributed Triage and Repair framework for RCA Agents in Microservices

Junle Wang, Ruibo Chen, Yuanshuai Wang, Xingchuang Liao, Zhimin Fan, Xiangdong Wu, Wenjun Wu, Jinkun Zhao et al.

按诊断阶段追踪 RCA 智能体的错误来源，并对推理过程进行定位和修复。

GRACE: A Strategic LLM-Enhanced Graph Reinforcement Learning Framework for Adaptive Fault Recovery in Microservice Systems

Ruibo Chen, Yanjun Pu, Ji Xin, Junle Wang, Xingchuang Liao, Kui Zhang, Wenjun Wu

结合大模型、图强化学习与恢复策略，实现微服务故障后的自适应处置。

CoE-Ops: Collaboration of LLM-based Experts for AIOps Question-Answering

Jinkun Zhao, Yuanshuai Wang, Xingjian Zhang, Ruibo Chen, Xingchuang Liao, Junle Wang, Lei Huang, Kui Zhang et al.

组织多个大模型专家协同回答 AIOps 问题，融合不同角色的运维知识和推理能力。

BERT4Anno: An Annotation Misuse Detection Method for Java

Jingbo Yang, Xin Ji, Wenjun Wu, Xingchuang Liao, Kui Zhang, Linxiao Dong, Nan Xiang, Ren Jian

利用预训练语言模型理解 Java 注解语义与上下文关系，检测潜在的注解误用。

SC-COO: A Feedback-Based Service Composition Algorithm Combining Offline and Online Reinforcement Learning

Xiaoming Yu, Wenjun Wu, Jiadong Wang, Xin Ji

结合离线学习与在线反馈，在动态环境中持续优化服务组合决策。

HMSC-LLMs: A Hierarchical Multi-Agent Service Composition Method Based on Large Language Models

Xingchuang Liao, Wenjun Wu, Xiaoming Yu, Xin Ji, Yiting Chen, Junting Li

采用分层多智能体结构分解复杂需求，并利用大模型协同完成大规模服务组合。

Graph-Based Ensemble Learning for Enhanced Fault Localization in Microservices

Ruibo Chen, Fang Peng, Xin Ji, Nan Xiang, Yihua Lou, Kui Zhang, Yanjun Pu, Wenjun Wu

通过图表示与集成学习融合多类运行信号，提高微服务故障定位的稳定性。

ELAKT: Enhancing Locality for Attentive Knowledge Tracing

Yanjun Pu, Fang Liu, Rongye Shi, Haitao Yuan, Ruibo Chen, Tianhao Peng, Wenjun Wu

结合自注意力与因果卷积聚合、平滑学生知识状态，并通过预测校正降低随机行为噪声，提升知识追踪与学习表现预测能力。

An Automatic Model Management System and Its Implementation for AIOps on Microservice Platforms

Ruibo Chen, Yanjun Pu, Bowen Shi, Wenjun Wu

面向微服务 AIOps 自动组织模型的训练、部署和生命周期管理。

Integrating Cognition Cost With Reliability QoS for Dynamic Workflow Scheduling Using Reinforcement Learning

Xiaoming Yu, Wenjun Wu, Yangzhou Wang

在动态工作流调度中联合考虑认知成本与可靠性 QoS，并用强化学习优化选择。

MicroEGRCL: An Edge-Attention-Based Graph Neural Network Approach for Root Cause Localization in Microservice Systems

Ruibo Chen, Jian Ren, Lingfeng Wang, Yanjun Pu, Kaiyuan Yang, Wenjun Wu

用边注意力图神经网络建模微服务依赖关系，从复杂故障传播中定位根因。

Dependable Workflow Scheduling for Microservice QoS Based on Deep Q-Network

Xiaoming Yu, Wenjun Wu, Yangzhou Wang

利用深度 Q 网络为微服务工作流选择兼顾可靠性与服务质量的调度方案。

API Misuse Detection Method Based on Transformer

Jingbo Yang, Jian Ren, Wenjun Wu

通过 Transformer 建模 API 使用上下文，识别可能引发软件缺陷的调用模式。

Parallelizing Automatic Model Management System for AIOps on Microservice Platforms

Ruibo Chen, Wenjun Wu

通过并行化模型管理流程提升微服务 AIOps 中自动分析任务的处理效率。

Workflow Recommendation Based on Graph Embedding

Xiaoming Yu, Wenjun Wu, Xingchuang Liao

把工作流及其组件关系编码为图表示，为服务流程提供结构感知的推荐。

Multi-Indicators Prediction in Microservice Using Granger Causality Test and Attention LSTM

Suozhao Ji, Wenjun Wu, Yanjun Pu

结合因果检验与注意力时序模型预测微服务指标，为异常预警提供支持。

Learning to Handle Exceptions

Jian Zhang, Xu Wang, Hongyu Zhang, Hailong Sun, Yanjun Pu, Xudong Liu

通过神经网络学习 Java 代码中的异常处理模式，预测 try 块位置并生成 catch 处理代码，辅助开发者完善程序异常处理。

Structural entropy guided hierarchical symmetric multi-agent reinforcement learning

Yongkai Tian, Xin Yu, Yirong Qi, Li Wang, Pu Feng, Wenjun Wu, Rongye Shi, Jie Luo

群体智能、层次对称性、多智能体强化学习

Offline constrained policy optimization with safe anchoring

Diyuan Hou, Longyang Huang, Pu Feng, Wenjun Wu

离线强化学习、安全约束优化

Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning

Li Wang, Changhao Zhang, Zengqi Xiu, Kai Lu, Xin Yu, Kui Zhang, Wenjun Wu

问题空间映射、小模型推理、强化学习

Lyapunov-Informed Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks

Pu Feng, Rongye Shi, Size Wang, Qizhen Wu, Xin Yu, Wenjun Wu

Lyapunov 稳定性、多机器人协作、多智能体强化学习

Symmetry-Informed MARL: A Decentralized and Cooperative UAV Swarm Control Approach for Communication Coverage

Rongye Shi, Xin Yu, Yandong Wang, Yongkai Tian, Zhenyu Liu, Wenjun Wu, Xiao-Ping Zhang, Manuela M. Veloso

对称先验、无人机群体控制、通信覆盖

Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding

Pu Feng, Size Wang, Yuhong Cao, Junkang Liang, Rongye Shi, Wenjun Wu

大模型、神经算法推理、多智能体路径规划

Exploiting Hierarchical Symmetry in Multi-Agent Reinforcement Learning

层次对称性、等变策略、多智能体强化学习

AdaptAUG: Adaptive Data Augmentation Framework for Multi-Agent Reinforcement Learning

Xin Yu, Yongkai Tian, Li Wang, Pu Feng, Wenjun Wu, Rongye Shi

自适应数据增强、多智能体强化学习

Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks

Pu Feng, Junkang Liang, Size Wang, Xin Yu, Xin Ji, Yiting Chen, Kui Zhang, Rongye Shi et al.

分层共识、多机器人协作、多智能体强化学习