Zijing Shi

About Me

I’m a third-year Ph.D. student at AAII UTS, supervised by Prof. Ling Chen. I am also fortunate to be advised by A/Prof. Meng Fang at the University of Liverpool.

My research focuses on building intelligent agents that are not only efficient but also trustworthy in open environments. Specifically, I work on:
1) Designing LLM- and RL-based agents for natural language interaction;
2) Exploring value alignment and bias mitigation in these agents.

News

• [Jan. 2025] One paper has been accepted at ICLR conference.
• [Dec. 2024] One co-authored paper has been accepted at NAACL 2024 conference.
• [Dec. 2024] One co-authored paper has been accepted at AAMAS 2025 (Short paper).
• [Jun. 2024] One co-authored paper has been accepted at ECAI conference.
• [May 2024] One co-authored paper has been accepted at ACL 2024 findings.
• [Dec. 2023] One co-authored paper has been accepted at AAAI 2024 (Main Track).
• [Dec. 2023] One paper has been accepted at AAAI 2024 (Oral, SRRAI Track).
• [Dec. 2023] Achieved HDR WiEIT (Women in Engineering and IT) Award.
• [Oct. 2023] Achieved 1st place in School of Computer Science Research Showcase.
• [Apr. 2023] One co-authored paper has been accepted at the ACL 2023 conference.
• [Jan. 2023] One paper has been accepted at the EACL 2023 conference.
• [Jan. 2023] One paper has been accepted at the ICLR 2023 conference.

Show More

Selected Papers

ICLR

Monte Carlo Planning with Large Language Models for Text‑based Game Agents

Zijing Shi, Meng Fang, Ling Chen

ICLR 2025.

PDF Code

AAAI

Large Language Models are Neurosymbolic Reasoners

Meng Fang*, Shilong Deng*, Yudi Zhang*, Zijing Shi, Ling Chen, Mykola Pechenizkiy, Jun Wang

AAAI 2024.

PDF Code

AAAI

Human‑Guided Moral Decision Making in Text‑based Games

Zijing Shi, Meng Fang, Ling Chen, Yali Du, Jun Wang

AAAI (Oral) 2024.

PDF Code

ACL

CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models

Jiaxu Zhao*, Meng Fang*, Zijing Shi, Yitong Li, Ling Chen, Mykola Pechenizkiy

ACL 2023.

PDF Code

ICLR

Stay Moral and Explore: Learn to Behave Morally in Text‑based Games

Zijing Shi*, Meng Fang*, Yunqiu Xu, Ling Chen, Yali Du

ICLR 2023.

PDF Code

EACL

Self‑imitation Learning for Action Generation in Text‑based Games

Zijing Shi, Yunqiu Xu, Meng Fang, Ling Chen

EACL 2023.

PDF Code

Teaching and Services

Teaching

• 2024: Teaching Assistant – Introduction to Artificial Intelligence, UTS (Undergraduate 41040; Postgraduate 42172)
• 2024: Teaching Assistant (Online) – Oxford Machine Learning Summer School (OxML)

Journal Reviewer

• Neural Computing and Applications
• IEEE Transactions on Artificial Intelligence

Conference Reviewer

• 2025: ICLR, ICML, NeurIPS, AAAI, COLM, ACL, EMNLP
• 2024: ICLR, ICML, NeurIPS, AAMAS, ACL, EMNLP