← Search

Takayuki Ito

2 accepted papers

2026

Position: LLM-Based Social Simulations Require a Boundary

ICML 2026poster

This position paper argues that **LLM-based social simulations require clear boundaries to make meaningful contributions to social science**. While Large Language Models (LLMs) offer promising capabilities for simulating human behavior, their tendency to produce homogeneous outputs, acting as an "av…

Cited by 0Source ↗Scholar ↗
2025

The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems

EMNLP 2025

Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature homogenization. We argue that implicit consensus, where agents exchang