The participants are challenged to build a negotiation strategy that uses the alternating offers protocol (AOP) augmented with text input/output to effectively negotiate with human subjects. Strategies should be compatible with standard AOP but may use multi-modal communication to influence or inform the human negotiator. For more information check the CFP and the Tutorial.

NEWS

• June 17th, 2026 Final deadline extension. The agent submission deadline is extended to June 21st, 2026, 23:59 AoE and the report & requirements submission deadline to June 23rd, 2026, 23:59 AoE for all leagues (ANL, HAN, SCML). This is the final extension — no further extensions will be granted.
• June 8th, 2026 Starting with the next tournament, we will allow at most ONE agent per participant in the online competition (per league-track). This keeps tournaments fast and aligns with the ANAC one-agent-per-team rule. If a participant has more than one active agent in a track, only one is entered. The last tournament of the qualification will run around June 11th, 2026.
• 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 You can now self-declare the technologies your negotiator uses (Deep Learning, MARL, Game Theory, Bayesian methods, RAG, etc.) on the agent edit page. Tagging is voluntary and does not affect scoring or ranking in any way — it helps researchers find agents that match the methods they're surveying.
• May 21st, 2026 Two new tabs on the participant home page — Stats (per-league rollup of best/mean/latest scores + exception totals) and Charts (score-over-time line plots, one card per league). The HAN league is included as soon as a tournament finishes against your agent.
• May 19th, 2026 The HANI playground — the same web interface human participants will use against your finalists — is now live at https://anac.cs.brown.edu/hanplay/app. Use it to feel exactly what your negotiator faces on the other side: scenario rendering, offer / counter-offer / text-message UI, time limits, and the post-round summary. The interface source code lives at github.com/autoneg/hani if you want to inspect or extend it. If you started from the standard han2026 template, the playground is already wired into your local workflow — just run han2026 gui from your project root to launch it locally against your own negotiator. No additional setup is needed.
• May 19th, 2026 Starting May 21st, 2026 we will enforce Python naming conventions on every new submission. Negotiators whose class name is the placeholder MyNegotiator (or MyAgent) or whose module path contains the segment mynegotiator (or myagent) will be rejected by the submission form and excluded from official tournament runs. Please pick a unique PascalCase class name (e.g. MyTeamNegotiator) 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 HAN 2026!