ΑΙhub.org
 

#IJCAI2019 mini-interviews – Claus Aranha from University of Tsukuba


by
14 August 2019



share this:

Meet Claus Aranha, Assistant Professor at the University of Tsukuba, Center of Artificial Intelligence Research (C-AIR).

What are you presenting at IJCAI?
I am organizing the werewolf track ANAC Competition.

 

Can you tell me more about ANAC?
ANAC stands for Automated Agent Negotiation Competition<sup>1</sup>. It is a competition where AI Agents negotiate with each other and/or humans. We have 6 leagues this year – Supply Chain Management, Werewolf (a social party game), Diplomacy (a board game), Human-Agent League, Agent-Agent League: Agent Negotiation with Partial Preferences and the GENIUS league.

 

What is the real world impact of agents negotiating with each other?
Take for example the Supply Chain Management (SCM) league. Right now in the SCM industry many stakeholders – from people who sell the raw material, to factories which produce goods, to shops who sell them are involved. Each one has their preferences on what they wish to get out of the deal and what they are ready to compromise on. They have to coordinate (i.e. negotiate) with each other all the time for timelines, prices, quantities, etc. It is a cumbersome and cognitively heavy job! 

Imagine a group of AI agents representing each stakeholder does this for you. Wouldn’t things become easier?

 

You said something about the werewolf track. Could you say more?
It is a social party game where agents are supposed to find who the werewolf is<sup>2</sup> in a setting where agents lie to each other and/or hide the truth about themselves. How can an agent deal with other agents who behave this way while the agent itself is also deceiving other agents — It is a hard challenge!

We had 90 teams this year out of which 70 sent an agent to the competition. We have 15 finalists and the top three will be discussed tomorrow (August 15)! Keep an eye out 🙂

 

How can I get involved?
Check out the AI Wolf project page3. You can also get some sample code here – https://github.com/caranha/AIWolfCompo

 

1http://web.tuat.ac.jp/~katfuji/ANAC2019/

2https://en.wikipedia.org/wiki/Mafia_(party_game)

3http://aiwolf.org/en/




Rahul Divekar is a PhD Candidate at the Department of Computer Science at Rensselaer Polytechnic Institute.
Rahul Divekar is a PhD Candidate at the Department of Computer Science at Rensselaer Polytechnic Institute.

            AUAI is supported by:



Subscribe to AIhub newsletter on substack



Related posts :

monthly digest

AIhub monthly digest: October 2026 – neurosymbolic planning, time-series forecasting, and robots for the home

  30 Oct 2026
Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
AI pioneers

From teaching machines to teaching people: an interview with Michael Littman

  29 Oct 2026
AI Pioneer Michael Littman reflects on the evolution of reinforcement learning, the power of science communication, and how generative AI is changing the way we teach and learn.

From lab to life: Why translating AI advances to the real world is a major challenge

  28 Oct 2026
Systems that perform well in controlled lab settings often fall short when deployed in homes, in hospitals or on city streets.

Researchers get AI ‘drunk’ to expose new cyber security risks in chatbots

Fine-tuning large language models using drunken text makes them more likely to leak secrets and answer harmful questions.

AI is creating jobs as well as erasing them – but how rewarding are they?

  26 Oct 2026
One area of increased employment is in people “cleaning up” after LLMs, or quality controlling them.

How AI changes human decision-making

  23 Oct 2026
AI can identify patterns that people miss and bring new information into decision-making. However, this does not automatically lead to better decisions.

Competing in RoboCup@Home and winning the 2026 best paper award: an interview with Raphael Memmesheimer

  22 Oct 2026
Hear more about Raphael's research and his involvement in the RoboCup@Home league.

AI is distorting archaeology and flattening Indigenous Knowledge

While AI can help archaeologists, it can also spread pseudoscientific claims and false histories, stripping Indigenous Knowledge of context, consent and community control.


↑


AUAI is supported by:







Subscribe to AIhub newsletter on substack




 















©2026.05 - Association for the Understanding of Artificial Intelligence