Home

About Me

I am a PhD candidate in Computer Science at the University of New South Wales (UNSW), Sydney, supervised by Prof. Flora Salim, A/Prof. Hao Xue, and A/Prof. Imran Razzak. I hold a Master of Data Science and Decisions from UNSW and a Bachelor of Engineering in Software Engineering from Beihang University.

My research lies at the intersection of knowledge graphs, large language models, and multi-agent systems. I focus on retrieval-augmented generation for complex, multi-step reasoning over heterogeneous evidence (text, tables, and KGs), self-evolving agents, spatio-temporal reasoning, and trustworthy personal agentic AI.

News

  • Three papers accepted at EMNLP 2026: SPLIT-RAG to the Main Conference, and GuardianAgent and RELOOP to Findings. (Aug 2026)
  • KG-IRAG was selected for an oral presentation at The Web Conference (WWW) 2026. (Jun 2026)
  • Released three new preprints: TrajPrism on language-grounded urban trajectories, STAR on failure-aware multi-agent routing, and MAGE on self-evolving agents with co-evolutionary knowledge graphs. (May 2026)
  • Started in the GuardianAgent project as a Research Officer at UNSW. (Jul 2025)
  • SSTKG accepted for oral presentation at WWW 2024. (2024)

Education

  • University of New South Wales, Sydney

    PhD in Computer Science

  • University of New South Wales, Sydney

    Master of Data Science and Decisions — with Excellence

  • Beihang University, Beijing

    Bachelor of Engineering in Software Engineering

Experience

  • University of New South Wales

    Research Officer — GuardianAgent

  • UNSW Sydney

    Casual Academic (Tutor)

    DATA9001 Data Science Fundamentals COMP9517 Computer Vision
  • Cresstec Pty Ltd

    Software Engineer Intern

  • Jina AI

    Software Engineer Intern

Publications

  • Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning

    Ruiyi Yang, Hao Xue, Imran Razzak, Shirui Pan, Hakim Hacid, Flora D. Salim.

    EMNLP, 2026.  Main Conference

  • GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalation

    Ruiyi Yang, Gayathri Lihinikaduarachchi, Rahat Masood, Flora D. Salim, Salil S. Kanhere.

    EMNLP, 2026.  Findings

  • RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA

    Ruiyi Yang, Hao Xue, Imran Razzak, Hakim Hacid, Flora D. Salim.

    EMNLP, 2026.  Findings

  • Beyond Single Pass, Looping Through Time: KG-IRAG with Iterative Knowledge Retrieval

    Ruiyi Yang, Hao Xue, Imran Razzak, Flora D. Salim.

    ACM Web Conference (WWW), 2026.  Oral

  • Route by State, Recover from Trace: STAR with Failure-Aware Markov Routing for Multi-Agent Spatiotemporal Reasoning

    Ruiyi Yang, Lihuan Li, Hao Xue, Flora D. Salim.

    Preprint, 2026.

  • MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs

    Ruiyi Yang, Zechen Li, Hao Xue, Imran Razzak, Flora D. Salim.

    Preprint, 2026.

  • TrajPrism: A Multi-Task Benchmark for Language-Grounded Urban Trajectory Understanding

    Lihuan Li, Wilson Wongso, Baiyu Chen, Hao Xue, Ruiyi Yang, Yifan Duan, Xiachong Lin, Yang Song, Flora D. Salim.

    Preprint, 2026.

  • SSTKG: Simple Spatio-Temporal Knowledge Graph for Interpretable and Versatile Dynamic Information Embedding

    Ruiyi Yang, Flora D. Salim, Hao Xue.

    ACM Web Conference (WWW), 2024.  Oral

Awards

  • ACM Web Conference Oral Presentation — KG-IRAG (2026)
  • UNSW Higher Degree by Research Scholarship (2024 – Present)
  • ACM Web Conference Oral Presentation — SSTKG (2024)
  • Master Degree with Excellence, UNSW (2023)

Service

  • Reviewer / sub-reviewer for venues including WWW, SIGIR, and related ML/IR workshops.
  • Co-supervision of "Taste of Research" projects with Prof. Flora Salim (UNSW).

Beyond Research

Outside of research, I enjoy languages — I studied French full-time for 1.5 years and hold the JLPT-N2 certificate in Japanese. I also co-authored Python Web Scraping: Practical Case Studies (Tsinghua University Press, 2023), contributing the chapter on application scenarios and data processing.

Beyond academia, I enjoy playing football and watching opera and ballet.