//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
To learn more: Website: agentcoma.github.io Preprint: arxiv.org/abs/2508.19988 A big thanks to my brilliant coauthors Lihu Chen, Ana Brassard, @joestacey.bsky.social, @rahmanidashti.bsky.social and @marekrei.bsky.social! Note: We welcome submissions to the #AgentCoMa leaderboard from researchers 🚀
9mo
AgentCoMa is an Agentic Commonsense and Math benchmark where each compositional task requires both commonsense and mathematical reasoning to be solved. The tasks are set in real-world scenarios:…
AgentCoMa
agentcoma.github.io
Lisa Alazraki