5 papers
Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races
Phu Hoa Pham, Duy Minh Dao Sy, Trung Kiet Huynh +9
An AI development race creates a multi-agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may remove its final reward. We use…
Payoff scaling shapes cooperation in LLM agents across languages
Trung-Kiet Huynh, Dao-Sy Duy-Minh, Thanh-Bang Cao +13
Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they cooperate in such settings is no lo…
EvoQRE: Modeling Bounded Rationality in Safety-Critical Traffic Simulation via Evolutionary Quantal Response Equilibrium
Phu-Hoa Pham, Chi-Nguyen Tran, Duy-Minh Dao-Sy +2
Existing traffic simulation frameworks for autonomous vehicles typically rely on imitation learning or game-theoretic approaches that solve for Nash or coarse correlated equilibria…
MEMRES: A Memory-Augmented Resolver with Confidence Cascade for Agentic Python Dependency Resolution
Dao Sy Duy Minh, Tran Chi Nguyen, Trung Kiet Huynh +3
We present MEMRES, an agentic system for Python dependency resolution that introduces a multi-level confidence cascade where the LLM serves as the last resort. Our system combines:…
Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics
Trung-Kiet Huynh, Duy-Minh Dao-Sy, Thanh-Bang Cao +13
As Large Language Models (LLMs) increasingly operate as autonomous decision-makers in interactive and multi-agent systems and human societies, understanding their strategic behavio…