← 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 0SourceScholar
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