The Sixth International Automated Negotiating Agents Competition

To be held in conjunction with the Nineth International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2015), Istanbul, Turkey, 4th-8th May 2015.


ANAC special session in ACAN2015 will be held on May 5th (Tue) at 16:30 in room B3-86.
ANAC session will be held on May 6th (Wed) at 16:30 in room Macka.
Please join us !


May 26, 2015: The results in the final round were revealed: here

April 29, 2015: ANAC special session in ACAN2015 will be held on May 5th (Tue) at 16:30 in room B3.86, and Automated Negotiating Agents Competition (ANAC) session will be held on May 6th (Wed) at 16:30 in room Macka.

April 17, 2015: The finalists are announced on the webpage: here

April 15, 2015: The notifications of the qualifying round are sent by e-mail.

April 1, 2015: There has been delays in announcing the final results because of some problems. Please wait momentarily until announcing the finalists.

February 10, 2015: We have fixed a bug recently and updated the Genius on the Website. Please download the newest Genius (5.2.2.).

We would like to know who are willing to participate in the competition. By registering your information via this form, we can inform about Genius update and ANAC2015 information and so on. Letting us about your intention to participate in ANAC 2015 is important for us.


Overview of ANAC2015

The ANAC competition brings together researchers from the negotiation community and provides a unique benchmark for evaluating practical negotiation strategies in multi-issue domains. The five 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. The goals of the competition are:

  • to encourage the design of practical negotiation agents that can proficiently negotiate against unknown opponents and in a variety of circumstances,
  • to provide a benchmark for objectively evaluating different negotiation strategies,
  • to explore different learning and adaptation strategies and opponent models, and
  • to collect state-of-the-art negotiating agents and negotiation scenarios, and making them available to the wider research community.



The participants of ANAC2015 will have to submit the completed registration form, Java code and class codes of the agent to R.Aydogan[at] and ANAC2015[at] i.e., the following files should be submitted:

  • A .tar, .tgz, .zip, or .jar file containing the agent sources and class files
  • A small description of the agant
  • A completed registration form. Download
Please submit the above files to R.Aydogan[at] and anac2015[at], directly.


Rules of Encounter

The aim for the entrants to the competition is to develop an autonomous negotiation agent. Performance of the agents will be evaluated in a tournament setting, where each agent is matched with all other submitted agents, and each triple of agents will negotiate in a number of linear negotiation scenarios. Negotiations are repeated several times to obtain statistically significant results.

Negotiations are multilateral and based on a multi-player version of the alternating-offers protocol. Offers are exchanged in real time with a deadline after 3 minutes. In addition, there will be a discount factor in about half of the domains, where the value of an agreement decreases over time. The challenge for an agent is to negotiate without any knowledge of the preferences and strategies of the opponents.

Agents can be disqualified for violating the spirit of fair play. The competition rules allow multiple entries from a single institution, but require each agent to be developed independently. Furthermore it is prohibited to design an agent which benefits some other specific agent. In particular, the following behaviors are strictly prohibited:

  • Designing an agent in such a way that it benefits some specific other agent.
  • Communicating with the agent during the competition.
  • Altering the agent during the competition.


The negotiation tournament was run using the java-based GENIUS negotiation platform, which has been developed to facilitate research in the area of bilateral multi-issue negotiation. It has an open architecture that allows for easy development and integration of existing negotiating agents using design patterns. GENIUS can be used to simulate individual negotiation sessions as well as tournaments between negotiating agents in various negotiation scenarios. The core functionality of the system includes:

  1. specification of negotiation domains and preference profiles;
  2. simulation of a bilateral negotiation between agents;
  3. analysis of the negotiation outcomes and negotiation dynamics.

It furthermore allows the specification of negotiation domains and preference profiles by means of a graphical user interface.

The GENIUS platform, together with the agents and scenarios from the previous competitions are available for download. More information about the platform can be found at the GENIUS web page. The agents from the previous competitions are available.

Main updates with respect to ANAC 2014

This year, the challenge is to reach an agreement while negotiating with two opponents at the same time. This year, the utility functions are linear again, as they were in ANAC 2010-2013.

The multi-player protocol is a simple extension of the bilateral alternating offers protocol, called the Stacked Alternating Offers Protocol for Multi-Lateral Negotiation (SAOPMN). According to this protocol, all of the participants around the table get a turn per round; turns are taken clock-wise around the table. The first party starts the negotiation with an offer that is observed by all others immediately. Whenever an offer is made the next party in line can take the following actions:

  • Make a counter offer (thus rejecting and overriding the previous offer)
  • Accept the offer
  • Walk away (e.g. ending the negotiation without any agreement)

This process is repeated in a turn taking clock-wise fashion until reaching an agreement or reaching the deadline. To reach an agreement, all parties should accept the offer. If at the deadline no agreement has been reached, the negotiation fails.

Qualifying Round and Finals:

There will be no qualifying rounds. The teams of the top 8 performing agents will be notified, and the final results will be announced at the AAMAS conference.

It is expected that teams that make it through to the finals will have a representative attending the AAMAS 2015 conference. Each team in the final will have the opportunity to give a brief presentation describing their agent.



We selected 13 finalists out of 24 submissions, which were evaluated using both individual utility and nash product in the qualifying round.
Individual Utility Nash Product
agentBuyogV2 (Nanyang Technological University)
PokerFace (TU Delft)
Atlas3 (Nagoya Institute of Technology)
XianFaAgent (Nanyang Technological University)
kawaii (Nagoya Institute of Technology)
ParsAgent (University of Isfahan)
RandomDance (Tokyo University of Agriculture and Technology)   
PhoenixParty (The Chinese University of Hong Kong)
agentBuyogV2 (Nanyang Technological University)
Mercury (Maastricht University)
AgentX (Nagoya Institute of Technology)
Atlas3 (Nagoya Institute of Technology)
CUHKAgent2015 (The Chinese University of Hong Kong)
JonnyBlack (University of Tulsa)
RandomDance (Tokyo University of Agriculture and Technology)   
AgentH (Nagoya Institute of Technology)


Results (Final Round)

Here is the results of the final round in ANAC2015.

Individual Utility

Average Standard Deviation
Atlas3 0.481042722 0.00156024
ParsAgent 0.470693979 0.003128712
RandomDance 0.46062548 0.003038258
kawaii 0.460129481 0.002715924
agentBuyog 0.458823101 0.003842303
PhoenixParty 0.442975836 0.005032221
XianFaAgent 0.353133027 0.001918821
PokerFace 0.344003999 0.001433044

Nash Product

Average Standard Deviation
Atlas3 0.323992201 0.000405256
Mercury 0.321600864 0.001620108
JonnyBlack 0.313749314 0.001026152
AgentX 0.312427823 0.001393852
CUHKAgent 0.309464847 0.001726555
RandomDance 0.294950885 0.001088483
AgentH 0.292136808 0.001547118
agentBuyog 0.282378625 0.00236416

Please see the slides for the details: Slide for the ANAC session in AAMAS2015


Questions and Answers

Feel free to ask your questions!
Please see the following link: here



The ANAC2015 will be held at the Istanbul Congress Center Istanbul, Turkey.
Taskisla Caddesi Harbiye 34367 Istanbul/ Turkiye


Organising Committee

  • Dr. Reyhan Aydogan, Delft University of Technology
  • Dr. Tim Baarslag, Delft University of Technology
  • Prof. Katsuhide Fujita, Tokyo University of Agriculture and Technology
  • Dr. Koen Hindriks, Delft University of Technology
  • Prof. Dr. Takayuki Ito, Nagoya Institute of Technology
  • Prof. Dr. Catholijn Jonker, Delft University of Technology



The prize money will be at least 500 Euro. The prize will be shared among the top agents in two categories: (1) winners in terms of individual utility, and (2) winners in terms of social welfare (measured by obtaining the highest average product of utilities of both parties).



Makoto lab. Inc.



For any questions, the main contact is Dr. Reyhan Aydogan <R.Aydogan[at]>