Takayuki Ito お茶です
Tea! ☕

Takayuki Ito

Doctor of Engineering

Professor
Department of Social Informatics, Graduate School of Informatics
Computer Science Course, Department of Informatics, Faculty of Engineering
Kyoto University  ·  Room 424, Building No. 7

Recent News

  • — 📄 New research statement: Research Statement 2026, "Consensus Building and Agent Governance in the Age of AI: Legitimacy, Mechanism Design, and Human Challenge" (Japanese version).
  • — Paper accepted: Shun Okuhara and Takayuki Ito, "On the Complexity and Encoding Footprint of Variable-Elimination Relaxation in Over-Constrained DisCSPs," IEICE Transactions on Information and Systems, 2026
  • — Paper accepted: Shun Okuhara and Takayuki Ito, "Computational Complexity of Threshold-Based Agreement Admissibility in Automated Negotiation," IEICE Transactions on Information and Systems, 2026
  • — Paper accepted: Roshia and Rafik Hadfi and Takayuki Ito, "Planted Claims Pull the Price: Misinformation Outweighs Facts for LLM Procurement Agents," The 1st International Workshop on Multi-Agent and Agentic Systems (MASO 2026), co-located with PRIMA 2026, 2026, Kumamoto, Japan
  • — 🎤 Facilitator: led Breakout Discussion Group B "AI, Data, and the Redefinition of Collaboration Boundaries: Ownership, Access, and Value Creation in the AI Era" at UIDP Japan 2026, Hibiya International Building Conference Square, Tokyo, Japan. Link
  • — 🎤 Keynote: Keynote speech (fireside chat) at the WEB300 Annual Conference 2026 "Tradition × Technology × Tomorrow" hosted by the MUNG network of law firms, followed by the AI Expert Panel "How AI Agents Will Change Your Business," QUESTION (The Kyoto Shinkin Bank), Kyoto.
  • — Paper accepted: Sofia Sahab and Jawad Haqbeen and Takayuki Ito, "AI facilitation and affective dynamics of online deliberation," Discover Psychology, 2026
  • — Paper accepted: Tianyou Gao and Takayuki Ito, "Beyond Node Influence: Activating Nested Subgraphs in Propagation Networks," ACM Transactions on Knowledge Discovery from Data (TKDD), 2026
  • — Paper accepted: Tianyou Gao and Takayuki Ito, "On Optimizing Route-Responsive Urban Tree Placement in City-Scale Pedestrian Networks," In Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD2026), 2026, Jeju, Korea
  • — Paper accepted: Wu, Peng, Ito, Onizuka & Xiao, "LLM-Based Social Simulations Require a Boundary," ICML 2026 (Position Paper Track).
All news →

Selected Papers

Communications Psychology (Nature Portfolio)·2024
Sofia Sahab, Jawad Haqbeen, Rafik Hadfi, Takayuki Ito, Richard Imade, Susumu Ohnuma, Takuya Hasegawa

A field study in Afghanistan in which members of different ethnic groups took part in online discussions facilitated by a conversational AI agent. Participants showed reduced interethnic prejudice and intergroup anxiety afterwards, providing evidence that AI-facilitated e-contact can support reconciliation in a conflict-affected society.

Group Decision and Negotiation·2021 2023 Gregory Kersten GDN Journal Best Paper Award
Takayuki Ito, Rafik Hadfi, Shota Suzuki

Introduces an automated facilitation agent that keeps large-scale online discussions productive: it reads the evolving argument structure of a debate and posts facilitation messages that encourage participants to add issues, ideas, and reasons. The system has been deployed in real civic discussions, showing how AI can help crowds reach consensus.

IJCAI 2007·Hyderabad, India, pp. 1347–1352
Takayuki Ito, Mark Klein, Hiromitsu Hattori

Proposes a negotiation protocol for agents whose preferences over multiple interdependent issues form nonlinear utility spaces, where classical linear negotiation methods break down. Agents sample high-utility regions of their own space and submit them as bids, and a mediator searches for combinations that maximize social welfare. This work launched the “complex automated negotiation” research line behind ACAN and ANAC.

AAMAS 2006·pp. 1151–1158 Best Paper Award
Takayuki Ito, David Parkes

Addresses auctions with interdependent values, where a bidder’s valuation depends on information held privately by other bidders. Building on the contingent-bids model, the paper gives a concrete, computationally tractable auction design in which truthful bidding remains a dominant strategy, bringing this theoretical model into practical mechanism design. Selected as Best Paper out of 553 submissions.

All publications → Top-tier conference papers →

About

Takayuki Ito is a Professor at the Department of Social Informatics, Graduate School of Informatics, Kyoto University. He works on multi-agent systems and artificial intelligence, with a focus on automated negotiation, computational mechanism design, and AI support for large-scale consensus building. He leads the development of D-Agree, an online discussion platform in which an AI agent facilitates crowd-scale deliberation; it has been used in civic discussions in Japan and in field studies in Afghanistan. This work is part of a research vision he calls “Hyperdemocracy,” which is also realized in X-Agree (D-AgreeX), an agentic web forum in which multiple AI agents support discussion and consensus building. His recent work studies LLM-based agents for negotiation, deliberation, and social simulation. His honors include the Prizes for Science and Technology from the Minister of MEXT (2013 and 2026), the JSPS Prize (2014), the MEXT Young Scientists’ Prize (2007), and the Best Paper Award at AAMAS 2006.

Dr. Takayuki Ito is Professor of Kyoto University. He received the B.E., M.E., and Doctor of Engineering from the Nagoya Institute of Technology in 1995, 1997, and 2000, respectively. From 1999 to 2001, he was a research fellow of the Japan Society for the Promotion of Science (JSPS). From 2000 to 2001, he was a visiting researcher at USC/ISI (University of Southern California / Information Sciences Institute).

From April 2001 to March 2003, he was an associate professor at Japan Advanced Institute of Science and Technology (JAIST). From 2004 to September 2020, he was at Nagoya Institute of Technology, becoming a full professor in 2014. Since October 2020, he is a Professor at Kyoto University. He was also an Honorary Professor at the University of Wollongong, Australia (2022–2025), has been an Associate Member of the Science Council of Japan since 2023, and an Adjunct Professor at Guangzhou University, China, since 2024.

From 2005 to 2006, he was a visiting researcher at Harvard University (Division of Engineering and Applied Science) and at the Center for Coordination Science, MIT Sloan School of Management. From 2008 to 2010, he was a visiting researcher at the Center for Collective Intelligence, MIT Sloan School of Management.

He is a board member of IFAAMAS, Executive Committee Member of IEEE Computer Society Technical Committee on Intelligent Informatics, and has served as PC-Chair of AAMAS2013, PRIMA2009, and General Chair of PRIMA2014. He is a senior member of ACM and IEEE.

Core Research Question: "Why can people reach consensus?" and "What is consensus?"

Research Interests

Multi-Agent Systems Automated Negotiation Collective Intelligence Crowd Intelligence Consensus Building Group Decision Support Computational Mechanism Design Game Theory Auction Theory Intelligent Agents Distributed Artificial Intelligence Agent-mediated Electronic Commerce Information Economics LLM Agents Reasoning under Uncertainty

Selected Awards

  • 2026 — Prizes for Science and Technology (Research Category), Commendation for Science and Technology by the Minister of MEXT — "Study on Consensus Support Systems based on AI Agents" (with Rafik Hadfi & Sofia Sahab) KU News →
  • 2025 — Best Paper Award, KICSS2025 — Sahab et al., "Conversational AI Agents for Mental Well-Being"
  • 2023 — Gregory Kersten GDN Journal Best Paper Award — Ito, Hadfi & Suzuki, Group Decision and Negotiation Journal (IF=2.648)
  • 2023 — JSAI Annual Conference Excellence Award, Japan Society for Artificial Intelligence (2023)
  • 2022 — Best Award, Kyoto University Summer Design School 2022 (GPT-3 and Social System Design)
  • 2021 — ANAC SCML OneShot Track — 3rd Place in the World (Yuchen Liu, Rafik Hadfi, Takayuki Ito)
All awards →

Contact

Address

Prof. Takayuki Ito, Ph.D.
Department of Social Informatics
Graduate School of Informatics
Kyoto University
Yoshida-Honmachi, Kyoto 606-8501, Japan

Room 424, Building No. 7

Get in Touch

TEL: +81-75-753-4821 (Direct)
FAX: +81-75-753-4820 (Direct)

Email: ito [at] i.kyoto-u.ac.jp

🔬 Lab Homepage
📄 Download CV (PDF)