Design and build an autonomous agent that negotiates on behalf of a factory manager situated in a supply chain management simulation. The goal of a factory manager in SCML is to maximize its profit given its private production capabilities by negotiating trades with other agents. A factory manager can engage in several negotiations simultaneously, for which its utility functions are in general interdependent. These negotiations, and any ensuing contracts, are bilateral. Moreover, they are private to the agents involved. For more details about the competition, please check the SCML 2026 standard track overview or SCML 2026 oneshot track overview.

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 agent uses (Deep Learning, RL, Search, Optimization, Game Theory, RAG, etc.) on the agent edit page. Tagging is voluntary and does not affect scoring or ranking in any way — it just helps researchers find agents that match the methods they're surveying.
• May 21st, 2026 New on your participant home page: Stats and Charts tabs — per-league rollup (runs, best/mean/latest score, best rank, exception counts) plus a score-over-time line chart for each league (SCML Standard, OneShot, ANL, HAN).
• May 19th, 2026 Starting May 21st, 2026 we will enforce Python naming conventions on every new submission. Agents whose class name is the placeholder MyAgent (or MyNegotiator) or whose module path contains the segment 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) 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 SCML 2026!

Getting started and getting help

1. The first thing you need to do is to read the game overview for the track you plan to submit to. You can check this year's rules for the one shot track and/or the standard track.
2. If you are not registered here, do so to received updates and be able to submit your agents later here.
3. After deciding which track(s) to participate in, check there detailed description ( OneShot or Standard ).
4. Next, Check the tutorials. You can find video tutorials and consult the documentation and we are happy to see you joining the discussions.
5. Next, Download the appropriate skeleton (OneShot Classic, RL or Standard Classic) and test it. You will find a full description on how to do that in the README as well as the docstring on top of myagent.py in the skeleton .
6. Happy hacking :-) If you have any questions, bug reports, feature requests, etc, you can open an issue on the SCML GitHub page