Research.

Intelligence, shaped together.

AI-POWERED COLLECTIVE INTELLIGENCE

Cooperative intelligence.
New possibilities for society.

From consensus building, automated negotiation and mechanism design to social simulation, we study the collective intelligence of people and AI through theory and real-world applications.

Agent-based Crowd Decision Support

We support crowd decision-making with agent technology. We have developed the systems Collagree and D-agree, which are used in the real world. Building on them, our current CREST project studies a new form of democracy platform.

Automated Negotiating Agents

Research on agents that negotiate autonomously. We explore negotiation theory starting from the fundamental question of what negotiation is, design negotiation models, and implement automated negotiating agents based on those models.

Computational Mechanism Design

We design mechanisms in which truthful reporting is the best strategy. Social institutions (mechanisms) are designed with game theory and microeconomics; in particular we design new mechanisms from an informatics viewpoint and clarify and resolve open problems in classical theory.

Industrial Application with AI technologies

Through broad industry collaboration, we research and develop software that solves industrial problems in advanced ways. Recently we focus in particular on approaches using deep learning.

Argumentation Theory

Mathematical and theoretical research on logical argumentation among agents. Beyond existing logics of argumentation, we study topics such as acceptability under the influence of arguments, with real-world argumentation applications in mind.

Multiagent Simulation

We realize simulations of large-scale social systems with multiagent technology, built from collections of micro-level activity models. By linking social and physical systems in a multi-layer structure, we also aim at unified, comprehensive simulation.

Multiagent DRL for Cooperation

Multiple actors gain a real advantage only when appropriate cooperation emerges, as in the saying "two heads are better than one." To study the emergence of such cooperation, we are currently working on multiagent deep reinforcement learning.

Decision Making, Group Decision Making and Consensus

We study human decision-making, group decision-making and consensus building, and develop methods to support them. We focus on social networks and crowds in particular, and also tackle the problem of how to estimate and extract the preferences and opinions of individuals.

LLM × Multiagent

We explore multiagent negotiation, discussion and simulation with large language models as policies and participants, studying cooperative intelligence through interaction among diverse agents.

Explore research projects

The next intelligence
starts with us.

Let’s create the next intelligence, together.

Get in touch about joining our lab or collaborating on research.

For prospective research students
Takayuki Ito Laboratory (Consensus Informatics)
Department of Social Informatics, Graduate School of Informatics
Kyoto University
Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan
+81-75-753-4820 (secretary)
contact@agent.soc.i.kyoto-u.ac.jp ↗
Google Maps ↗