MSc. and PhD. student Vacancy for Tübitak 1001 Research Project is available !
This project, Design, Development, and Evaluation of an Intelligent Meta-Agent Capable of Negotiating in Natural Language, is a 36-month initiative funded by The Scientific and Technological Research Council of Turkey (TÜBİTAK) under the 1001 project program.
The core of this project is to create a sophisticated negotiation agent that is capable of negotiating in natural language by fusing traditional, strategic negotiation mechanisms with the power of Large Language Models (LLMs). The goals of the project can be summarized as follows:
- Natural Language Fluency: Using LLMs to understand, process, and generate human-like dialogue, arguments, and responses.
- Strategic Adaptivity: Leveraging the advanced reasoning capabilities of LLMs, combined with proven negotiation algorithms to dynamically analyze human sentiment, model opponent preferences, and adjust the underlying negotiation strategy in real-time.
- Evaluation: Developing a dedicated platform for negotiations in natural language to conduct our evaluations, using both simulations and user experiments to validate the agent’s performance.
Job Description
We are looking for a PhD or Postgraduate student to work together on the following fields:
- Argumentation
- Opponent Modelling
- Negotiation Strategies
- Natural Language Processing
- Large Language Models
- Multi-Agent Systems
We expect you to actively participate in the following tasks:
- Conducting high-quality research within the project
- Presentation of research findings at workshops and conferences
- Publication of scientific papers in peer-reviewed international journals
- Collaborate strongly with all peers
Requirements
- Specialization in artificial intelligence or related field
- Written and oral fluency in English
- Minimum of 3.00 GPA in undergraduate and minimum of 3.50 GPA in master’s degree
- An intermediate understanding of Software Engineering ( e.g., Python, Github )
- An intermediate understanding of Machine Learning (e.g., Hugging Face, PyTorch)
Nice to Have’s:
- Prior publications
- Familiarity with automated negotiation or multi-agent systems
- Agent Organization Frameworks (e.g., LangGraph, LangChain)
Dr. Reyhan Aydogan has received TÜBİTAK 1001 Research Project Grant.
Dr. Reyhan Aydogan is one of the AAMAS 2022 PC members awarded with the Best Senior PC Member Award. The AAMAS 2022 Area Chairs nominated candidates for this award and made the final selection of 14 Ordinary PC Members and 13 Senior PC Members that fairly represent all the AAMAS areas.
The 12th annual competition since 2010, ANAC 2021 (Automated Negotiating Agents Competition) was held online this year in conjunction with IJCAI 2021 (International Joint Conference on Artificial Intelligence). Our students of the School of Engineering, advised by Assistant Professor Reyhan Aydoğan and Professor Amy Greenwald at Brown University, were awarded the runner-up prize in two categories (standard and collusion track) which evaluated and awarded practical negotiation & production strategies in Supply Chain Management League (SCML).
Mehmet Onur Keskin and Gevher Yesevi, master’s students in the Artificial Intelligence Program of the Institute of Science and Technology, and Umut Çakan, a master’s student in the Computer Engineering Program of the same institute, designed an intelligent agent for supply chain management that can analyze the market and competitors’ behaviors and negotiate about price and quantity of products with the suppliers and customers according to production capabilities. They were awarded the second place prize with their team named Charlies’ Agent in SCML league conducted in cooperation with the NEC-AIST, Japan. We congratulate our students for their outstanding achievements and wish them all an academic life and a career full of achievements. In addition, we would like to thank the team advisors and Assistant Professor Emre Sefer for their fruitful feedback during the development of the agent.
http://web.tuat.ac.jp/~katfuji/ANAC2021/
Our paper titled “Solver Agent: Towards Emotional and Opponent-Aware Agent for Human-Robot Negotiation”, has been accepted to AAMAS 2021 as a poster paper. This paper proposes a bidding strategy for humanoid robots, which incorporates their opponents’ emotional states and awareness of the agent’s changing behavior. You can find the paper in the following link:
http://www.ifaamas.org/Proceedings/aamas2021/pdfs/p1557.pdf
- Winner of the HUMAINE League in ANAC 2020
We a
re pleased to inform you that our graduate students, Mehmet Onur Keskin and Umut Çakan participated in the Human Multi-Agent Immersive Negotiation League of the Eleventh International Automated Negotiating Agent Competition (ANAC 2020) under Asst. Prof. Dr. Reyhan Aydoğan’s supervision and won both categories (Individual & Social Welfare) of the contest. The team members designed and implemented a negotiating software agent that negotiates automatically against human negotiators. Among five teams from the United States, Israel, and Turkey, our team Companion got the highest score. We congratulate our students for their outstanding achievements and wish them all an academic life and a career full of achievements. HUMAINE: https://cisl.rpi.edu/humaine2020
- Winner of the Automated Negotiation League in ANAC 2020
We are pleased to inform you that our undergraduate students, Ahmet Burak Yıldırım and Nezih Sunman participated in the Automated Negotiation League of the Eleventh International Automated Negotiating Agent Competition (ANAC 2020) under Asst. Prof. Dr. Reyhan Aydoğan’s supervision and won the contest. The team members designed and implemented a negotiating software agent that negotiates automatically against other software agents. Among the thirteen teams from various countries (e.g. United States, Japan, Israel, United Kingdom, Turkey, etc.), our team AhBuNe Agent, got the highest individual agent score. We congratulate our students for their outstanding achievements and wish them all an academic life and a career full of achievements.
-
Our Bachelor’s and Master’s Degree Students Receive Two Awards in ANAC 2017
- “Modern Approaches to Agent-based Complex Automated Negotiation” by Springer is now available online. http://www.springer.com/in/book/9783319515618
- We are pleased to inform that our Computer Engineering undergraduate students, Burak Atalay, Taha Doğan Güneş ve Bahadır Kırdan participated in the Seventh International Automated Negotiating Agent Competition (ANAC 2016) under Asst. Prof. Dr. Reyhan Aydoğan’s supervision and won the contest. The team members designed and implemented a negotiating software agent that negotiates automatically against other software agents. Among the sixteen teams, our team Caduceus, “the symbol of commerce”, got the highest score. We congratulate our students for their outstanding achievement and wish them all an academic life and a career full of achievements. About Automated Negotiating Agent Competition: The ANAC competition is a yearly-organized international competition in conjunction with AAMAS and aims to bring together researchers from the negotiation community and to provide a unique benchmark for evaluating practical negotiation strategies in multi-issue domains. The previous competitions have spawned novel research in AI in the field of autonomous agent design, which are available to the wider research community. The focus of this year’s competition is on multi-party negotiation in smart energy grids.
- International Workshop on Conflict Resolution in Decision Making, COREDEMA 2016 will be held in conjunction with ECAI 2016, The Hague, The Netherlands (29-30 August, 2016).
- The Seventh International Automated Negotiating Agents Competition ANAC 2016 will be held in conjunction with AAMAS 2016, Singapore (May 9-12, 2016).
- International Workshop on Agent-based Complex Automated Negotiations ACAN 2016 will be held in conjunction with AAMAS 2016, Singapore (May 9-10, 2016)
- International Conference on Agents (ICA 2016) will be held in Japan (September 28-30, 2016)
