Yuxuan Li

Yuxuan Li 李宇轩

Humans increasingly delegate agency to machines such as large language models in social contexts, creating the need for socially intelligent language agents. I lead the following research advancing this field:

Individual level: How socially intelligent are language agents, and how can we improve them?
EMNLP'25 Oral, FAccT'25, ICLR'26 Submission

Collective level: How well can language agents simulate human societies, and how can we make these simulations genuinely useful for real-world practice?
ToCHI Submission, PoliSim@CHI'26, USENIX SEC'26 Submission

I hold a BS in Computer Science from Tsinghua University, advised by Chun Yu and Yuanchun Shi. I was also a research intern at UC Berkeley, advised by Coye Cheshire. My research has received extensive media coverage and led to invited talks at institutions such as CMU, Georgia Tech, Tsinghua, HKU and Microsoft.

Citation

@inproceedings{li-shirado-2025-spontaneous,
    title = "Spontaneous Giving and Calculated Greed in Language Models",
    author = "Li, Yuxuan  and
      Shirado, Hirokazu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.267/",
    doi = "10.18653/v1/2025.emnlp-main.267",
    pages = "5271--5286",
    ISBN = "979-8-89176-332-6",
    abstract = "Large language models demonstrate strong problem-solving abilities through reasoning techniques such as chain-of-thought prompting and reflection. However, it remains unclear whether these reasoning capabilities extend to a form of social intelligence: making effective decisions in cooperative contexts. We examine this question using economic games that simulate social dilemmas. First, we apply chain-of-thought and reflection prompting to GPT-4o in a Public Goods Game. We then evaluate multiple off-the-shelf models across six cooperation and punishment games, comparing those with and without explicit reasoning mechanisms. We find that reasoning models consistently reduce cooperation and norm enforcement, favoring individual rationality. In repeated interactions, groups with more reasoning agents exhibit lower collective gains. These behaviors mirror human patterns of ``spontaneous giving and calculated greed.'' Our findings underscore the need for LLM architectures that incorporate social intelligence alongside reasoning, to help address{---}rather than reinforce{---}the challenges of collective action."
}

Yuxuan Li 李宇轩

Selected Papers

What Makes LLM Agent Simulations Useful for Policy? Insights From an Iterative Design Engagement in Emergency Preparedness

Citation

Spontaneous Giving and Calculated Greed in Language Models

Selected Media Coverage

Citation

Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models

Citation

HiddenBench: Assessing Collective Reasoning in Multi-Agent LLMs via Hidden Profile Tasks

Citation

A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples

Citation

Say Your Reason: Extract Contextual Rules In Situ for Context-aware Service Recommendation

Citation