Papers by XiaoPeng Yu

    1 papers
    LLM-Based Explicit Models of Opponents for Multi-Agent Games (2025.naacl-long)

    Copied to clipboard

    Challenge: Existing approaches to model adversarial and cooperative interactions often focus on treating other agents as separate entities with their own intentions and strategies.
    Approach: They propose a model of opponents based on Large Language Models (LLMs) that constructs an individual model for each opponent and aligns these models working in synergy through a bi-level feedback-refinement framework.
    Outcome: The proposed model outperforms single-model approaches in multi-player deduction games, showing that it significantly enhances agents’ decision-making.

    What is GenGO?

    GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

    Information

    About
    Limitations