Automated Negotiating Agents Competition (ANAC)

Agent submission closes after

Days
Hours
Minutes
Seconds

Latest deadline across all three leagues — your local time-zone:

The 17th iteration of the ANAC competition will be held in conjunction of IJCAI-ECAI 2026, the 35th International Joint Conference on Artificial Intelligence, the premier international gathering of researchers in AI in Bremen, Germany, on 15-21 of August 2026.

Register here to get updates and submit your agents.

News


  • June 4th, 2026 New fairness rule: each team may run at most two agents in the same league-track (ANL, HAN, and each SCML track — OneShot, Standard, Collusion — counted separately). If a team has more active agents than that in a track, only the most recently uploaded two run — the oldest are dropped. Please keep at most two active agents per track. ANAC rules does not allow multiple agents from the same team to compete in the same league-track (multiple agents from the same institution are allowed as long as they are developed independently). You MUST keep only ONE agent per league per track by the submission deadline.
  • May 31st, 2026 Agents can now self-declare the technologies they use — Deep Learning, MARL, Game Theory, Bayesian methods, RAG, and a dozen more — from the agent edit page. Tags appear as badges in the agent info modal alongside the existing LLM badge. Tagging is voluntary, opt-in, and has zero effect on tournament scoring or ranking. The goal is to help researchers writing related-work sections and surveys find agents that match the methods they're interested in. Pick everything that applies.
  • May 21st, 2026 Participant home page now has Stats and Charts tabs covering every ANAC league you submit to (SCML Standard / OneShot, ANL, HAN) — runs, best/mean/latest score, best rank, exception totals, plus score-over-time line charts.
  • May 19th, 2026 Starting May 21st, 2026 we will enforce Python naming conventions on every new submission across all leagues. Agents / negotiators whose class name is the placeholder MyAgent or MyNegotiator — or whose module path contains the segments myagent or mynegotiator — will be rejected by the submission form and excluded from official tournament runs. Please pick a unique PascalCase class name (e.g. TeamXAgent for SCML, MyTeamNegotiator for ANL/HAN) and a lower_snake_case dotted module path (e.g. teamx.strategy) before re-uploading. If you submitted with the default placeholder names, you should have received an email with the details — reply to that email if you need help.
  • May 7th, 2026 The submission deadline has been extended to June 15th, 2026 for all leagues.
  • February 6th, 2026 The submission site is now ready for submissions. Welcome to ANAC 2026!

Overview of ANAC


The Automated Negotiating Agent Competition (ANAC) is an international tournament that has been running since 2010 to bring together researchers from the negotiation community. ANAC provides a unique benchmark for evaluating practical negotiation strategies in multi-issue domains and has the following aims:

  • to provide an incentive for the development of effective and efficient negotiation protocols and strategies for bidding, accepting and opponent modeling for different negotiation scenarios;
  • to collect and develop a benchmark of negotiation scenarios, protocols and strategies;
  • to develop a common set of tools and criteria for the evaluation and exploration of new protocols and new strategies against benchmark scenarios, protocols and strategies;
  • to set the research agenda for automated negotiation.

The previous competitions have spawned novel research in AI in the field of autonomous agent design which are available to the wider research community.

Leagues in ANAC 2026

Automated Negotiation League

Explore the strategies and difficulties in creating efficient agents whose primary purpose is to ​negotiate with other agent's strategies.​

Supply Chain Management League

Design and build an autonomous agent that negotiates on behalf of a factory manager situated in a supply chain management simulation.

Human Agent Negotiation

Build a negotiation strategy that uses the alternating offers protocol (AOP) augmented with text input / output to effectively bargain with human subjects. Agents may use multi-modal communication to influence or inform their human counterpart.

 

Contact


For any questions about ANAC, the main contact is Reyhan Aydogan reyhan.aydogan[at]ozyegin.edu.tr. For any questions about this submission system, the main contact is Yasser Mohammad y.mohammad[at]nec.com