Speaker: Fernando Santos (Informatics Institute, University of Amsterdam)
Date: Wednesday 29 July 2026 (16.00–17.00 UTC)
About: Fernando Santos examines how reputation sustains cooperation through indirect reciprocity. He explores evolutionary game theory, reinforcement learning across social groups, and how LLM-based reputation systems influence cooperation dynamics.
FINAL WEEK TO APPLY: We're Hiring an Administration Associate!
You’ll play a vital, behind-the-scenes role in a range of activities - from helping deliver our PhD Fellows programme to managing end-to-end logistics for our events. If you bring strong administrative or operations experience, thrive on bringing order to complexity, take pride in getting the details right, and want your work to matter, we'd love to hear from you.
Location: Remote, with opportunities to meet the team every few months. We're expecting to appoint someone based in the UK.
Salary: We expect salaries offered to be between £50,000 and £55,000.
Find out more and apply: https://www.cooperativeai.com/job-listing/administration-associate
Niklas Lauffer will talk at the Cooperative AI Foundation's next ‘Fellows’ Spotlight’. He recently completed his PhD at UC Berkeley and will be joining Google DeepMind as a research scientist.
About: This talk explores how to make adversarial training work in cooperative multi-agent settings by ensuring agents remain rational, thus preventing self-sabotage - a critical failure mode in these types of settings - while still discovering adversarial examples, improving robustness, and learning diverse policies.
Title: Benchmarking Offline RL in Mixed-Motive Social Settings Date: Thursday 21 May, 16:00 UTC Speaker: Claude Formanek (University of Cape Town) About: Reinforcement learning is increasingly applied to social, data-limited environments where agents must interact with others without the luxury of online experimentation. However, standard offline RL benchmarks are non-social. This seminar introduces Molten Pot, a benchmark for offline mixed-motive social RL that spans five substrates from DeepMind's Melting Pot environment and ~1TB of trajectory data. Testing agents across three levels of social complexity reveals a significant ‘social robustness gap’.
Title: Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems Date: Thursday 23 April, 16:00 UTC Speaker: Sahar Abdelnabi(ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems) About: Sahar will present findings from applying Colosseum, a principled new framework to study collusion in multi-agent settings by jointly analysing communications and actions in rich yet verifiable environments.
The Cooperative AI Foundation is kicking off a 'Fellows’ Spotlight' seminar series featuring the most exciting research from our Cooperative AI PhD Fellows. Make sure to register for our first seminar:
Title: Safe Pareto Improvements: Cooperative Commitments without Compromise Thursday 26 March, 17:00 UTC Speaker: Nathaniel Sauerberg (University of Texas at Austin) About: Advanced AI systems may introduce many new ways to credibly commit to and enforce agreements in strategic interactions. However, because players may disagree on what constitutes a mutually beneficial outcome, Safe Pareto Improvements address this by adjusting payoffs without altering the structure of the game—ensuring that outcomes improve for all while avoiding coordination problems.
Register for the seminar: https://www.cooperativeai.com/seminars/safe-pareto-improvements-seminar
This is an advanced programme for early-career professionals already working in or studying cooperative AI. Over five intensive days, participants will attend talks by leading researchers and work on collaborative projects tackling real cooperative AI challenges. Financial assistance is available, and we especially encourage people from underrepresented groups to apply.
Join the Cooperative AI Foundation's next ‘Updates in Cooperative AI’ seminar with Fernando Santos (Informatics Institute, University of Amsterdam).
https://www.cooperativeai.com/seminars/cooperation-through-reputation-in-multi-agent-systems
Cooperative AI Foundation
FINAL WEEK TO APPLY: We're Hiring an Administration Associate!
You’ll play a vital, behind-the-scenes role in a range of activities - from helping deliver our PhD Fellows programme to managing end-to-end logistics for our events. If you bring strong administrative or operations experience, thrive on bringing order to complexity, take pride in getting the details right, and want your work to matter, we'd love to hear from you.
Location: Remote, with opportunities to meet the team every few months. We're expecting to appoint someone based in the UK.
Salary: We expect salaries offered to be between £50,000 and £55,000.
Find out more and apply: https://www.cooperativeai.com/job-listing/administration-associate
Niklas Lauffer will talk at the Cooperative AI Foundation's next ‘Fellows’ Spotlight’. He recently completed his PhD at UC Berkeley and will be joining Google DeepMind as a research scientist.
About: This talk explores how to make adversarial training work in cooperative multi-agent settings by ensuring agents remain rational, thus preventing self-sabotage - a critical failure mode in these types of settings - while still discovering adversarial examples, improving robustness, and learning diverse policies.
Hi everyone! Make sure to join the Cooperative AI Foundation's next seminar:
Title: Benchmarking Offline RL in Mixed-Motive Social Settings
Date: Thursday 21 May, 16:00 UTC
Speaker: Claude Formanek (University of Cape Town)
About: Reinforcement learning is increasingly applied to social, data-limited environments where agents must interact with others without the luxury of online experimentation. However, standard offline RL benchmarks are non-social. This seminar introduces Molten Pot, a benchmark for offline mixed-motive social RL that spans five substrates from DeepMind's Melting Pot environment and ~1TB of trajectory data. Testing agents across three levels of social complexity reveals a significant ‘social robustness gap’.
Register for the seminar
Sharing the Cooperative AI Foundation's next seminar in our 'Updates in Cooperative AI' series:
Title: Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Date: Thursday 23 April, 16:00 UTC
Speaker: Sahar Abdelnabi (ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems)
About: Sahar will present findings from applying Colosseum, a principled new framework to study collusion in multi-agent settings by jointly analysing communications and actions in rich yet verifiable environments.
Register for the seminar
The Cooperative AI Foundation is kicking off a 'Fellows’ Spotlight' seminar series featuring the most exciting research from our Cooperative AI PhD Fellows. Make sure to register for our first seminar:
Title: Safe Pareto Improvements: Cooperative Commitments without Compromise
Thursday 26 March, 17:00 UTC
Speaker: Nathaniel Sauerberg (University of Texas at Austin)
About: Advanced AI systems may introduce many new ways to credibly commit to and enforce agreements in strategic interactions. However, because players may disagree on what constitutes a mutually beneficial outcome, Safe Pareto Improvements address this by adjusting payoffs without altering the structure of the game—ensuring that outcomes improve for all while avoiding coordination problems.
Register for the seminar: https://www.cooperativeai.com/seminars/safe-pareto-improvements-seminar
Update from the Cooperative AI Foundation: Summer School 2026
The Cooperative AI Summer School 2026 ‘Expression of interest’ applications are now open! Taking place in Canada (location TBA) from 3-7 August. Watch last year’s recap video for a flavour on what to expect.
This is an advanced programme for early-career professionals already working in or studying cooperative AI. Over five intensive days, participants will attend talks by leading researchers and work on collaborative projects tackling real cooperative AI challenges. Financial assistance is available, and we especially encourage people from underrepresented groups to apply.
Find out more and apply by 22 March 2026 (11.59pm AoE) on the Cooperative AI website.