Milind Tambe

YouTube video by The Circuit News Engineers Use AI to Save Animals! Watch Two Heroes in Action!

Happy to see this video about our PAWS project using AI for conservation. Also highlights Prof Sara Beery's work

youtube.com/watch?v=UhF-...

What does 'agentic' AI mean? Tech's newest buzzword is a mix of marketing fluff and real promise For technology adopters looking for the next big thing, “agentic AI” is the future. At least, that’s what the marketing pitches and tech industry T-shirts say.

My views on "agentic" here in this AP article on "agentic AI"

apnews.com/article/agen...

I thoroughly enjoyed my keynote on "AI for social good and public health" as well as engaging audience interaction at the SMASH symposium at MILA Montreal. Great concept to create this wonderful interdisciplinary symposium.

Enjoyed my lecture and questions from the audience today October 28 at the 30th Anniversary Speaker Series for the Georgia Health Policy Center. My talk: "AI for Social Good and Population Health: Bandit Algorithms, Social Networks and Agents".

How can we ... use machine learning to enhance anti-poaching measures? Features a quote and photo of Charles Emogor. Read the blog post to find out more.

📢 New blog! @charlesemogor.bsky.social uses machine learning to enhance anti-poaching across sub-Saharan Africa.

Working with @anil.recoil.org, @fletcherecology.bsky.social and @milindtambe-ai.bsky.social, he is developing models to help rangers patrol effectively.

Find out more: bit.ly/4mMs3Av

YouTube video by USC Center for AI in Society Milind Tambe, USC CAIS Seminar, September 16, 2025

Last week I had a wonderful visit to University of Southern California for my seminar on "Optimizing social impact: Field deployments, bandit algorithms, and the role of LLM agents". Big thank you to @sac.usc.edu and USC CAIS center. Video of my lecture below:

www.youtube.com/watch?v=yYYq...

Looking forward to visiting University of Southern California next week for this seminar.

Calling for care: How AI is answering India’s maternal health crisis Dr Milind Tambe, Director, Google DeepMind, talks about how machine learning is personalising healthcare for millions of Indian mothers—one phone call at a time

I was thrilled to speak to "The Hindu Business Line" news about our work on AI for maternal health.

www.thehindubusinessline.com/info-tech/ca...

Making every call count: How AI is supporting mothers in India Predictive AI models built with pro bono support from Google DeepMind researchers are helping strengthen maternal health information programs.

Just sharing a recent blog post that offers some insights into a project our team has been working on. It highlights how AI is being used in a partnership between Google DeepMind and ARMMAN to improve maternal health in India.

blog.google/intl/en-in/c...

YouTube video by Easy Conferences AAMAS 2026 | 25th International Conference on Autonomous Agents and Multiagent Systems

The 25th International Conference on Autonomous Agents and Multiagent Systems is coming to Cyprus this year.

youtu.be/aAGHxUPZInY

#AAMAS2026 #Cyprus #AutonomousAgents

What a truly special day at Convocation Hall at the University of Toronto! Feeling so grateful for the honor of being the convocation speaker for the remarkable Class of 2025 from the Faculty of Information and Faculty of Music.

Wishing all the graduates the very best on their journey forward!

Even though Tonghan Wang couldn't be here in person, I was incredibly fortunate to virtually hood him as my latest PhD student, alongside his co-advisor, Professor and Dean David Parkes, at the Harvard John A. Paulson School of Engineering and Applied Sciences.

Really fortunate to be hooding my 40th PhD student, Sanket Shah, at the Harvard John A. Paulson School of Engineering and Applied Sciences in person yesterday. This year, the ceremony felt even more special.

Looking forward to Sanket's exciting future research contributions.

Should LLMs be used to review papers? AAAI is piloting LLM-generated reviews this year. I wrote a blog post arguing that using LLMs as reviewers can have bad downstream consequences for science by centralizing judgments about what constitutes good research.

bryanwilder.github.io/files/llmrev...

Congratulations!!

Our two papers this morning at AAMAS2025:

Bayesian Collaborative Bandits with Thompson Sampling for Improved Outreach in Maternal Health
(Ambassador)

On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow
(Richard)

@aamasconf.bsky.social

Kicking off our #AAMAS25 coverage with a reminder that the registration desk on the 3rd floor is open until 7pm tonight. Follow the sign to get your lanyards!

Looking for a principled evaluation method for ranking of *general* agents or models, i.e. that get evaluated across a myriad of different tasks?

I’m delighted to tell you about our new paper, Soft Condorcet Optimization (SCO) for Ranking of General Agents, to be presented at AAMAS 2025! 🧵 1/N

I am at AAMAS 2025! @aamasconf.bsky.social

Never missed an AAMAS or prior to that ICMAS!

Gearing up for the final set of sessions before we wrap up Day 1 at #AAMAS25.

It's been a full day of workshops, tutorials, and great conversations - but we're not done yet. See you in the rooms for one last round!

#MultiAgentSystems #AIResearch #ALA2025

Huge congrats to PHD student Sanket Shah on his successful PhD defense, "Decision-Focused Learning for the Masses With Applications to Public Health"! 🎉 What a fantastic way to celebrate our Teamcore group's 30th anniversary, with Sanket becoming our group's 40th PhD!

Thrilled to be here in Singapore for #ICLR2025!

Find me:

Friday @ 3–5:30pm
Poster #416
RL with combinatorial actions

Friday @ 6:30pm
Panelist at CCAI x ETH event

Sunday @ 9am
Invited talk @ XAI4Science workshop

Monday all day
Hall 4 #3
Organizing @climatechangeai.bsky.social workshop

Our method combines deep RL with mixed-integer programming for sequential planning with combinatorial actions.

Can we use RL to plan with combinatorial constraints?

Our #ICLR2025 paper combines deep RL with mathematical programming to do so! We embed a trained Q-network into a mixed-integer program, into which we can specify NP-hard constraints.

w/ brwilder.bsky.social, Elias Khalil, Milind Tambe

Paper:
Deep RL + mixed integer programming to plan for restless bandits with combinatorial (NP-hard) constraints.

with @brwilder.bsky.social, Elias Khalil, @milindtambe-ai.bsky.social

Poster #416 on Friday @ 3–5:30pm

bsky.app/profile/lily...

If you are interested in advancing fundamental research in Multiagent Systems​ for applications in social impact, please see this​ position​ at Google Deepmind India:

job-boards.greenhouse.io/deepmind/jobs/…

​We are seeking a highly motivated Research Scientist to join our team in Bengaluru.