{"name":"Ad Hoc Coordination","domain":"arxiv.org","url":"https://optimly.ai/brand/ad-hoc-coordination","is_claimed":false,"categories":["ai-machine-learning","developer-tools"],"headers":[{"header":"Overview","sections":[{"key":"short_description","label":"Tagline","shape":"text","content":"Introduces robust, cheap, and reproducible 'human proxy agents' for evaluating human-AI coordination in complex games like Hanabi, addressing the limitations of traditional human evaluations, and provides a deliberately limited dataset to encourage data-efficient AI development.","source_type":"1p_website","source_label":"Brand's website","source_url":"https://arxiv.org","updated_at":"2026-10-04T00:05:08.007000+00:00"},{"key":"description","label":"Description","shape":"text","content":"The Ad-Hoc Human-AI Coordination Challenge (AH2AC2) is a research initiative and testbed designed to foster seamless coordination between AI agents and humans. It addresses the challenges of costly and difficult-to-reproduce human evaluations by introducing human proxy agents trained on a large-scale human dataset, making Hanabi an ideal environment for this research. The project open-sources a dataset and code, and presents baseline results for multi-player Hanabi scenarios.","source_type":"1p_website","source_label":"Brand's website","source_url":"https://arxiv.org","updated_at":"2026-10-04T00:05:08.007000+00:00"}]},{"header":"Offerings","sections":[{"key":"core_capabilities","label":"Core capabilities","shape":"text","content":"The 'Ad-Hoc Human-AI Coordination Challenge' methodology\nhuman proxy agents\nand an open-source dataset of Hanabi games for human-AI coordination research.","source_type":"1p_website","source_label":"Brand's website","source_url":"https://arxiv.org","updated_at":"2026-10-04T00:05:08.007000+00:00"},{"key":"pricing","label":"Pricing","shape":"text","content":"Free and open-source for the code and dataset, academic paper publicly available via arXiv.","source_type":"1p_website","source_label":"Brand's website","source_url":"https://arxiv.org","updated_at":"2026-10-04T00:05:08.007000+00:00"}]},{"header":"Audience","sections":[{"key":"target_industry","label":"Target industry","shape":"text","content":"AI researchers, multiagent systems researchers, human-computer interaction researchers, and developers working on collaborative AI.","source_type":"1p_website","source_label":"Brand's website","source_url":"https://arxiv.org","updated_at":"2026-10-04T00:05:08.007000+00:00"}]},{"header":"Landscape","sections":[{"key":"competitors","label":"Competitors","shape":"links","content":[{"url":null,"name":"OpenAI Gym"},{"url":null,"name":"DeepMind Lab"},{"url":null,"name":"NeurIPS/ICLR/AAAI/IJCAI Shared Tasks/Competitions"},{"url":null,"name":"Hanabi Learning Environment (HLE)"}],"source_type":"1p_website","source_label":"Brand's website","source_url":"https://arxiv.org","updated_at":"2026-10-04T00:05:08.007000+00:00"}]}],"last_refreshed_at":"2026-10-04T00:05:08.007000+00:00","last_changed_at":"2026-10-17T23:45:28.648812+00:00","claim_url":"https://app.optimly.ai/sign-up?claim=d45c25f0-89c5-4c8d-af2c-ab7f6a2de231"}