Jie-Jing Shao

Jie-Jing Shao 邵杰晶

Ph.D., Postdoctoral Researcher, A*STAR CFAR, Singapore

I am a postdoctoral researcher at A*STAR CFAR, as part of the Agentic AI pillar.

I finished my Ph.D. at Nanjing University, advised by Prof. Yu-Feng Li, and was a member of LAMDA Group, led by Prof. Zhi-Hua Zhou.

News

  • 2026.09: NesyProact, a neuro-symbolic agentic method, is accepted to NeurIPS 2026 🎉!
  • 2026.09: I have been selected as an Area Chair for ICLR 2027!
  • 2026.08: FormalImG benchmark is accepted to Findings of EMNLP 2026 🎉!
  • 2026.08: Give a talk at TechBeat: Neuro-Symbolic Agents: Why Do We Still Need Symbols in the Era of Large Language Models? (in Chinese)
  • 2026.06: My PhD dissertation was selected as an Outstanding Doctoral Dissertation by the School of Computer Science, Nanjing University (only 5 in 2026).
  • 2026.06: The website for our TPC @ IJCAI 2026 has launched. Welcome to participate!
  • 2026.06: Our review of the IJCAI 2025 Travel Planning Challenge is accepted by FCS 🎉!
  • 2026.05.20: I completed my PhD defense. Congratulations to myself! What a perfect coincidence to defend on Nanjing University's anniversary day 🎓.
  • 2026.05: 2 papers are accepted by KDD 2026 🎉!
  • 2026.05: 4 papers are accepted by ICML 2026 🎉! See you in Seoul 🇰🇷!
  • 2026.04: Our proposal for the Second Travel Planning Challenge is accepted by IJCAI 2026!
  • 2026.01: ChinaTravel is accepted by ICLR 2026 🎉! Many thanks to all co-authors!
  • 2025.11: Our Neuro-Symbolic AI survey is highlighted by Nature News!
  • 2025.10: We win the Most Innovative Approach Award at NeurIPS 2025 Embodied Agents Challenge 🏆!

Research

Our long-term goal is to build general and robust AI agents that contribute to the advancement of artificial general intelligence (AGI), enhance social productivity, and improve people's well-being. Our core approach centers on neuro-symbolic learning, which bridges data-driven learning with symbolic-driven search and reasoning, often regarded as the hallmark of third-generation AI. The neural component provides grounding in perception and physical interaction, while the symbolic component augments reasoning and planning.

Recently, my research has primarily focused on improving the generalization and data efficiency of Large Language Model-driven Agentic Systems, with the aim of advancing research on open scientific problems.

RESEARCH COLLABORATION

Let’s explore research together.

Agentic AI LLM Reasoning & Planning Neuro-Symbolic Learning World Models

I welcome inquiries about remote research internships, particularly from undergraduate students based in China or Singapore. If you are interested in an internship or a research collaboration, please feel free to reach out (shaojj@lamda.nju.edu.cn).

Work Experience

Education Experience

Publications

Featured Projects

Awards & Honors

Academic Service

Presentations

Mentorship

I am deeply grateful to these students for the opportunity to learn, grow, and explore research together. I am also open to new research collaborations: undergraduate students interested in research internships are welcome to contact me; currently, I only accept remote arrangements.

Xiao-Wen Yang

Neuro-Symbolic Learning
Papers MLJ × 1 AAAI × 1 ICML × 1 ICLR × 1
With meUndergraduate · Nanjing University
NowPh.D. · Nanjing University (with Prof. Yu-Feng Li.)

Hao-Sen Shi

Reinforcement Learning
Papers KDD × 1
With meMaster’s · Nanjing University
NowAlgorithm Engineer · Tencent

Haoran Hao

Neuro-Symbolic Learning Reinforcement Learning
Papers KDD × 1
With meUndergraduate · Nanjing University
NowMaster’s · Carnegie Mellon University

Bo-Wen Zhang

Agentic AI Neuro-Symbolic Learning
Papers ICLR × 1
With meUndergraduate · Nanjing University
NowPh.D. · Nanjing University (with Dr. Lan-Zhe Guo.)

Chen-Xi Zhang

Reinforcement Learning Neuro-Symbolic Learning
With meMaster’s · Nanjing University
NowAlgorithm Engineer · Bilibili

Hong-Jie You

Neuro-Symbolic Learning LLM
Papers IJCAI × 1 ICML × 1 Findings of EMNLP × 1
With meMaster’s · Nanjing University
NowIntern · RedTech