I am a final-year Ph.D. student at the Natural Language Processing and Knowledge Engineering Group (NLPKE), Institute of Automation, Chinese Academy of Sciences (CASIA). I am fortunate to be advised by Prof. Jun Zhao. Before that, I obtained my B.E. degree in Software Engineering from Northeastern University (NEU) in 2021. My research interests include natural language processing, large language models, and knowledge engineering. I have published over 30 papers at top-tier conferences, including NeurIPS, ICLR, ACL, AAAI, EMNLP, NAACL, and COLING.

🔎 Research

My research aims to advance intelligent agent systems by making them knowledgeable, multimodal, controllable, and grounded in real-world environments. Specifically, my work focuses on three closely connected directions:

• Knowledge for Agent: Providing knowledge to agents through agentic environments and world models, enabling them to explore, interact, and accumulate experience.

• Agent for Knowledge: Developing agents for knowledge management and knowledge discovery, enabling them to actively collect, organize, analyze, and update knowledge.

• Social Intelligence: Applying agents to social simulation and social governance, enabling them to model, predict, and guide multi-agent interactions and emergent behaviors.

🔥 News

• 2026-06:  📰 We released a survey on Agentic Environment Engineering, which systematically summarizes recent progress in Environment Modeling, Synthesis, Evaluation, and Application, with nearly 600 papers reviewed.
• 2026-05:  🏆 I received the President Special Award of UCAS (57 students in UCAS).
• 2026-03:  🎉 Four papers are accepted by ACL 2026.
• 2026-03:  🎉 Four papers are accepted by ICLR 2026, including one selected as an Oral presentation (1.1%).
• 2025.09:  🎉 One paper is accepted by NeurIPS 2025.
• 2025.05:  🎉 Five paper are accepted by ACL 2025.

📝 Publications

Selected Publications

Survey

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Jiachun Li^*, Zhuoran Jin^*, Tianyi Men^*, Yupu Hao^*, Kejian Zhu^*, Lingshuai Wang^*, Dongqi Huang^*, Longxiang Wang^*, Shengjia Hua^*, Lu Wang^*, Jinshan Gao^*, Hongbang Yuan, Ruilin Xu, Kang Liu, Jun Zhao

ICLR 2026

Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Zhuoran Jin^*, Hongbang Yuan^*, Kejian Zhu^*, Jiachun Li, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

ICLR 2026

MMR-V: What’s Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos
Kejian Zhu, Zhuoran Jin, Hongbang Yuan, Jiachun Li, Shangqing Tu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

NeurIPS 2024

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
Zhuoran Jin, Pengfei Cao, Chenhao Wang, Zhitao He, Hongbang Yuan, Jiachun Li, Yubo Chen, Kang Liu, Jun Zhao

ACL 2024

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

2026

• Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do. ACL 2026.
  Zhuoran Jin, Kejian Zhu, Hongbang Yuan, Yupu Hao, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning. ACL 2026.
  Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• Towards Explainable Diagnosis: A Self-learned Explanatory Knowledge Base Approach. ACL 2026.
  Dongqi Huang, Tong Zhou, Zhuoran Jin, Shenghui Shi, maoyujiao, Kang Liu, Jun Zhao, Yubo Chen

• Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation. ACL Findings 2026.
  Yupu Hao, Zhuoran Jin, Huanxuan Liao, Kang Liu, Jun Zhao

• Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences. ICLR 2026 (Oral).
  Zhuoran Jin^*, Hongbang Yuan^*, Kejian Zhu^*, Jiachun Li, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning. ICLR 2026.
  Jiachun Li, Shaoping Huang, Zhuoran Jin, Chenlong Zhang, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• MMR-V: What’s Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos. ICLR 2026.
  Kejian Zhu, Zhuoran Jin, Hongbang Yuan, Jiachun Li, Shangqing Tu, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling. ICLR 2026.
  Jiachun Li, Pengfei Cao, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

2025

• RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality. NeurIPS 2025.
  Chenlong Zhang, Zhuoran Jin, Hongbang Yuan, Jiaheng Wei, Tong Zhou, Kang Liu, Jun Zhao, Yubo Chen

• Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents. ACL 2025.
  Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns. ACL 2025 (SAC Highlights).
  Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

• Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity. ACL 2025.
  Yupu Hao, Pengfei Cao, Zhuoran Jin, Huanxuan Liao, Yubo Chen, Kang Liu, Jun Zhao

• Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis. ACL 2025.
  Kejian Zhu, Shangqing Tu, Zhuoran Jin, Lei Hou, Juanzi Li, Jun Zhao

• RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment. ACL Findings 2025.
  Zhuoran Jin, Hongbang Yuan, Tianyi Men, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models. ICLR 2025.
  Jiachun Li, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

• DTELS: Towards Dynamic Granularity of Timeline Summarization. NAACL 2025.
  Chenlong Zhang, Tong Zhou, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

• Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models. NAACL Findings 2025.
  Hongbang Yuan, Yubo Chen, Pengfei Cao, Zhuoran Jin, Kang Liu

• Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models. AAAI 2025.
  Hongbang Yuan^*, Zhuoran Jin^*, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• CITI: Enhancing Tool Utilizing Ability in Large Language Models Without Sacrificing General Performance. AAAI 2025.
  Yupu Hao, Pengfei Cao, Zhuoran Jin, Huanxuan Liao, Yubo Chen, Kang Liu, Jun Zhao

2024

• RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024.
  Zhuoran Jin, Pengfei Cao, Chenhao Wang, Zhitao He, Hongbang Yuan, Jiachun Li, Yubo Chen, Kang Liu, Jun Zhao

• Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models. EMNLP 2024.
  Hongbang Yuan, Pengfei Cao, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

• Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models. EMNLP 2024.
  Tianyi Men, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Jun Zhao

• LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning. EMNLP Findings 2024.
  Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Jun Zhao

• AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation. EMNLP Findings 2024.
  Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Kang Liu, Jun Zhao

• Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning. ACL 2024.
  Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

• MULFE: A Multi-Level Benchmark for Free Text Model Editing. ACL 2024.
  Chenhao Wang, Pengfei Cao, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao

• Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models. ACL Findings 2024.
  Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao

• Tug-of-War between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models. COLING 2024.
  Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Qiuxia Li, Jun Zhao

• Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning. COLING 2024.
  Zhitao He, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, Jun Zhao

2023

• InstructoR: Instructing Unsupervised Conversational Dense Retrieval with Large Language Models. EMNLP Findings 2023.
  Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching. EMNLP Findings 2023.
  Zhuoran Jin, Pengfei Cao, Zhitao He, Yubo Chen, Kang Liu, Jun Zhao

• Zero-Shot Cross-Lingual Event Argument Extraction with Language-Oriented Prefix-Tuning. AAAI 2023.
  Pengfei Cao^*, Zhuoran Jin^*, Yubo Chen, Kang Liu, Jun Zhao

2022 and Earlier

• A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing. EMNLP 2022.
  Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

• CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding. EMNLP Demo 2022.
  Zhuoran Jin^*, Tianyi Men^*, Hongbang Yuan^*, Yuyang Zhou, Pengfei Cao, Yubo Chen, Zhipeng Xue, Kang Liu, Jun Zhao

• CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge. ACL Demo 2022.
  Zhuoran Jin^*, Tianyi Men^*, Hongbang Yuan^*, Zhitao He, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Yubo Chen, Jun Zhao

• CogIE: An Information Extraction Toolkit for Bridging Texts and CogNet. ACL Demo 2021.
  Zhuoran Jin, Yubo Chen, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Jun Zhao

🎖 Honors and Awards

• 2026, President Special Award, Chinese Academy of Sciences. (中国科学院院长特别奖，中科院研究生最高奖项)

• 2026, Outstanding Doctor Graduates, Beijing. (北京市优秀毕业生)

• 2026, Outstanding Graduates, University of Chinese Academy of Sciences. (中国科学院大学优秀毕业生)

• 2025, Wang Shouwu Scholarship, University of Chinese Academy of Sciences. (王守武奖学金)

• 2023, Second Prize of the Pandeng Scholarship, Institute of Automation. (攀登奖学金二等奖)

• 2022, Merit Student, University of Chinese Academy of Sciences. (中国科学院大学优秀学生)

• 2021, Outstanding Graduate, Liaoning Province. (辽宁省优秀毕业生)

💼 Services

• 2025-2026, Teaching Assistant of Knowledge Engineering, University of Chinese Academy of Sciences.

• 2022-2024, Student Executive Committee Member, Youth Working Committee, Chinese Information Processing Society of China. (中文信息学会青工委学生委员)

• 2023, Program Chair, The China Student Symposium on Natural Language Processing, CSSNLP 2023. (CSSNLP 2023 程序委员会主席)

• 2022, Program Chair, EMNLP 2022 Paper Pre-Presentation Session. (EMNLP 2022 论文预讲会主席)

• Regular reviewer for NeurIPS, ICLR, ICML, ACL, EMNLP, NAACL, and TNNLS.

📖 Educations

• 2021.09 - 2026.06, Ph.D., School of Artificial Intelligence, University of Chinese Academy of Sciences, supervised by Prof. Jun Zhao.

• 2017.09 - 2021.06, B.E., School of Software Engineering, Northeastern University.