Scholar
Run Peng
Google Scholar ID: dqTJFVcAAAAJ
University of Michigan
Citations & Impact
Citations
179
H-index
4
i10-index
4
Publications
9
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- ICML 2025 MAS Workshop: Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry
- Preprint: LLM-Based Social Simulations Require a Boundary
- CoLM 2025: Bootstrapping Visual Assistant Development with Situated Interaction Simulation
- CoLM 2025: Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation
- EMNLP 2023 Findings: Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models
- ICRA 2024: Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation
- ICML 2023: Go Beyond Imagination: Maximizing Episodic Reachability with World Models
- EMNLP 2024 Findings: Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents
- Preprint: Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations
- NeurIPS 2022 DRL Workshop: Learning Exploration Policies with View-based Intrinsic Rewards
Background
- Ph.D. candidate in Computer Science and Engineering at the University of Michigan, advised by Professor Joyce Chai. His primary research focus is to bridge the gap between humans and AI agents, exploring agent behaviors, human behaviors, and human-AI interaction when humans are cosituated with the agents.
Miscellany
- Overwatch Ana Player
