(1/3) Three Foundations of Cooperative AI Lab (FOCAL) at CMU papers at #AAAI2025! Starting with one from yesterday: Emery Cooper did a wonderful job presenting "Characterising simulation-based program equilibria." underline.io/events/473/ses… arxiv.org/abs/2412.14570

(2/3) Then, today at 2:30pm in the game theory session, Emin Berker will present "The Value of Recall in Extensive-Form Games." underline.io/events/473/ses… arxiv.org/abs/2412.19659

(3/3) And in the same session, Emanuel Tewolde will present "Computing Game Symmetries and Equilibria That Respect Them." underline.io/events/473/ses… arxiv.org/abs/2501.08905

Emanuel Tewolde (and coauthor Caspar Oesterheld) receiving the AAAI'25 best poster award from Professor Toby Walsh FAA FTSE, for our paper "Computing Game Symmetries and Equilibria That Respect Them" (also with Brian Zhang and Tuomas Sandholm)! arxiv.org/abs/2501.08905

article on CMU papers at CHI'25 including our work on AI and Moral Decision-Making (with Vijay Keswani, Walter Sinnott-Armstrong, Breanna Nguyen, Hoda Heidari, Jana Schaich Borg; CMU School of Computer Science Foundations of Cooperative AI Lab (FOCAL) at CMU) cs.cmu.edu/news/2025/chi2…

AAMAS 2025 begins! Today is our workshop on Social Choice for AI Ethics and Safety. The AAMAS Conference sites.google.com/view/sc4ai/wor…

Our Foundations of Cooperative AI tutorial at AAMAS is about to start (room Richard B)! All the materials are at the link below. Foundations of Cooperative AI Lab (FOCAL) at CMU The AAMAS Conference cs.cmu.edu/~conitzer/FOCA…

Looking forward to participating in the cooperative AI panel at AAMAS tonight! The AAMAS Conference Foundations of Cooperative AI Lab (FOCAL) at CMU

Human-aligned AI Summer School Human-aligned AI Summer School has an updated list of speakers Fazl Barez (Oxford) Lewis Hammond (Cooperative AI Foundation) Evan Hubinger (Anthropic) gavin leech (Future Intelligence) Nathaniel Sauerberg (Foundations of Cooperative AI Lab (FOCAL) at CMU) Noah Y. Siegel (Google DeepMind) Stanislav Fort and Torben Swoboda. Apply ~now

Join the first seminar in our new 'Updates in Cooperative AI' series exploring our recent 'Multi-Agent Risks' report, live June 26th (5pm BST, 9am PT, 12pm ET) alongside Lewis Hammond Gillian Hadfield Michael Dennis.

Looking forward to the 75 years of Nash equilibrium conference! I'll speak on game theory for AI agents. mfo.ac.uk/event/nash75-o…

(1/2) ACM SIGecom EC'25 has started! Two papers with coauthors from our Foundations of Cooperative AI Lab (FOCAL) at CMU: Learning and Computation of Phi-Equilibria at the Frontier of Tractability W 8:30am session Led by Brian Zhang and Ioannis Anagnostides arxiv.org/abs/2502.18582

(2/2) From Independence of Clones to Composition Consistency: A Hierarchy of Barriers to Strategic Nomination W 1:30pm session Led by Emin Berker&relevant to evaluating AI, where it is easy to create very similar variants of a given AI system ("clones"). arxiv.org/abs/2502.16973

A fantastic group of young researchers at the Cooperative AI Summer School, bodes well for the future of cooperative AI!

Want to know which game is better without making equilibrium selection assumptions? Caspar Oesterheld (Caspar Oesterheld) is about to present our Foundations of Cooperative AI Lab (FOCAL) at CMU paper at TARK, "Choosing What Game to Play Without Selecting Equilibria"! andrew.cmu.edu/user/coesterh/…

(1/2) Two papers with authors from our Foundations of Cooperative AI Lab (FOCAL) at CMU being presented at ICML ICML Conference in the next two days: Oral Wed 16:15 & Poster Wed 16:30 Expected Variational Inequalities (led by Brian Zhang and Ioannis Anagnostides). arxiv.org/abs/2502.18605

(2/2) Poster Thu 16:30 Observation Interference in Partially Observable Assistance Games (led by Scott Emmons and Caspar Oesterheld) -- a model of the human-AI value alignment problem which allows the human and the AI assistant to have partial observations. arxiv.org/abs/2412.17797

(1/n) I noticed that on the IMO where several LLM-based systems just got gold medals, the fifth problem (the last one solved by Gemini Deep Think) was a game problem, so I had no excuse :-) not to try it myself first and then see how the solutions compared.

The Nash75 talks are on YouTube! Below is my talk "Game Theory for AI Agents" (link also gives all other talks on the side). youtube.com/watch?v=WO5xJI…

short paper by Yoshua Bengio and me about what LLMs tell us about our own mental lives (extended from earlier blog post) philpapers.org/rec/YOSWDL