Roberta Raileanu

Open-Endedness Team Lead and Senior Staff Research Scientist @GoogleDeepMind. Adjunct Faculty @bold_lab_ai. ex @Meta | @NYU | @Princeton | IPhO | IOAA.

[Roberta Raileanu @robertarail]

I’m building a new team at @GoogleDeepMind to work on Open-Ended Discovery!

We’re looking for strong Research Scientists and Research Engineers to help us push the frontier of autonomously discovering novel artifacts such as new knowledge, capabilities, or algorithms, in an open-ended self-improving loop.

We aim to work on ambitious research projects in a fast-paced manner.

If this sounds appealing to you, apply using the link below by Friday, August 1st EOD:
https://t.co/xZHhjEoxHo

[Tom Zahavy @TZahavy]

We are looking for student researchers to work with us at the discovery team @GoogleDeepMind 👀👀👀

This is a great opportunity to work with Alex on scientific discovery 🔬

[Roberta Raileanu @robertarail]

Fantastic opportunity to do an internship with a great team and mentor!

[Alex Havrilla @Dahoas1]

🚀 Google DeepMind’s Discovery Team is hiring a Student Researcher for 2027!

You’ll be based in London and advised by me. We’re exploring the frontiers of:

• Scientific Discovery and formal methods
• Multi-Agent Systems
• Benchmarking & novel evaluation paradigms

[Roberta Raileanu @robertarail]

Our Open-Endedness team at @GoogleDeepMind has a few openings for Student Researchers.

Lei is a fantastic researcher and mentor, so please apply if you are interested in these topics!

[Lei M. Zhang @l32zhang]

I’m hiring a Student Researcher at
@GoogleDeepMind.

I am looking for PhD students working on multi-agent organization, open-endedness, or self-improvement.

📍 Location: Toronto
🗓️ Duration: 6 months, 100%
🚀 Start date: Jan 2027

Apply now using the links below👇

[Roberta Raileanu @robertarail]

Our Open-Endedness team at @GoogleDeepMind has a few openings for Student Researchers.

Maxence is a fantastic researcher and mentor, so please apply if you are interested in these topics!

[Maxence Faldor @maxencefaldor]

I’m hiring a Student Researcher at @GoogleDeepMind.

I am looking for PhD students working on agents, open-endedness, self-improvement or scientific discovery.

📍 Location: London
🗓️ Duration: 24 weeks, 100%
🚀 Start date: June or July 2027

Apply now using the links below👇

[Maxence Faldor @maxencefaldor]

I’ve had so much fun making bricky, and playing with it: a compiler for LEGO® models, built for AI agents.

The agent writes a Python build script. bricky places every part, reports each mistake, and renders the model.

Thanks to @omar_aflak for the idea of a LEGO® compiler.

[Roberta Raileanu @robertarail]

Great opportunity to work on AI safety and alignment with a fantastic advisor!

[Oana-Maria Camburu @oanacamb]

🚀 I am hiring a Postdoc in AI Safety & Alignment @imperialcollege to work on ⚡️Detecting Unverbalized Dangerous Capabilities in Frontier Models⚡, as part of a grant I received.

🗓️ Application Deadline: 22nd November
🔗 Link: https://t.co/ylL3thbz7g
📅 Start date: ASAP

[Roberta Raileanu @robertarail]

@GenReasoning Very exciting, congrats!!

[Alex Havrilla @Dahoas1]

Getting into the fantastic world of busy beaver cryptid hunting has been a highlight of my time on GDM's Discovery team. Who knew how much hidden structure could be living in such simple machines!

@dsantosmarco did a great job with this project, excited to see where it leads

[Tom Zahavy @TZahavy]

Over the past year, the Discovery team at @GoogleDeepMind, in a project led by student researcher @dsantosmarco, has made new discoveries in one of the most beautiful open problems at the edge of computation: Finding the 6th Busy Beaver (BB) number.

While most AI math systems solve human-generated problems, like theorems, this work tackles a different aspect of mathematical creativity: Discovering hidden problems.

For years, the BB Community has pursued one of theoretical computer science’s most captivating collaborative quests: finding the simplest programs that run the longest before halting. Because determining whether these programs ever stop is uncomputable, no universal algorithm can solve it, meaning new mathematical techniques need to be found and invented to make progress.

In this way, the BB challenge serves as an open ended domain for mathematical creativity and, in particular, a generator of hard math problems called Cryptids. These are tiny programs whose halting behavior is governed by and equivalent to deep, unsolved math problems in number theory, similar to the Collatz or Goldbach conjectures. Historically, the BB community had recognized ~20 Cryptids in BB(6), and the best problems were selected for the Busy Math Olympiad (BMO).

Building on their work, Marco built a pipeline powered by Gemini 4 Argon that:
1️⃣ Simulates raw Turing machine traces to compress recurring patterns.
2️⃣ Conjectures mathematical transition rules & runs synthetic experiments to test edge cases.
3️⃣ Proves the equivalence formally in Lean 4.

Using this pipeline, Marco and the team discovered 20 new potential Cryptids and verified 33 more machines previously studied in the BB community. All the proofs were open sourced and shared in the community discord channel and we hope that they will help the community to make progress towards resolving BB(6). We also contributed related halting/non-halting proofs directly to the community GitHub repository.

Finding these Cryptids shows hidden links between simple programs and number theory, and helps mathematicians map the limits of computation. I'm also excited about Gemini 4 Argon's ability to help researchers both solve hard problems and accelerate scientific discoveries, of which Busy Beaver is just one example.

Work led by our student researcher @dsantosmarco with paper contributions from @vivek_veeriah, @Dahoas1 , Andrew Bolt, @zuza777 , Satinder Singh, and myself with additional contributions from Hussain Masoom, @maxencefaldor , @MoritzFirsching and Petar Sirkovic.

Read more about it in our paper: https://t.co/KMRrDZh82L

[Roberta Raileanu @robertarail]

Congrats @TZahavy, @dsantosmarco, @Dahoas1, @maxencefaldor and team on collaborating with Argon and the community to make progress on Busy Beaver and cryptids! 🦫 🦫 🦫

[Maxence Faldor @maxencefaldor]

It has been a blast hunting cryptids with such a great team 👾

Alongside the Busy Beaver holdout proofs, we also open-sourced smaller 2-symbol Turing machines for three foundational math problems, verified end-to-end in Lean 4 from a blank tape to Mathlib (0 sorry):

- Goldbach's Conjecture: 25 -> 21 states
- Riemann Hypothesis: 120 -> 104 states
- ZF Consistency: 393 -> 380 states

Using Gemini Argon, we compressed the community baseline machines and proved both the state reductions and full mathematical semantics in the kernel: each machine halts if and only if the conjecture fails (or ZF is inconsistent).

Best part of releasing this openly: within days of going live, a community contributor already built on our 104-state proof to push the Riemann machine down to 95 states. 🚀

Huge thanks to everyone across the @GoogleDeepMind team who contributed to this project: @tomzahavy, @robertarail, @dsantosmarco, @vivek_veeriah, @Dahoas1, @zuza777, @MoritzFirsching, Andrew Bolt, Satinder Singh, Hussain Masoom, and Petar Sirkovic, as well as the Busy Beaver community.

Code: https://t.co/rL7NosqxAl

[raia hadsell @RaiaHadsell]

Congratulations to @maxencefaldor, @robertarail, Satinder Singh and the rest of the team! Four Gemini 4 Argon agents teamed up in Minecraft, writing code and sharing learnings for 27 hours to beat the Ender Dragon. A fantastic example of Argon's ability to plan, adapt, and solve complex problems as a team.

[Roberta Raileanu @robertarail]

@PetarV_93 @maxencefaldor Thank you, Petar! Multumim :)

[Roberta Raileanu @robertarail]

Four Gemini 4 Argon agents teamed up in Minecraft to defeat the Ender Dragon in 27 hours, writing every move as code and coordinating in the game's chat.

Great work led by @maxencefaldor with Satinder Singh.

Read more in our technical report:
https://t.co/QV9OZjSumu.

[Maxence Faldor @maxencefaldor]

Four Gemini 4 Argon agents, one shared Minecraft world, one goal: defeat the Ender Dragon. 27 hours and 2,783 self-written programs later, the dragon fell. https://t.co/Cx7Djg1VTx

[Tim Rocktäschel @_rockt]

Cool, after @NetHack_LE now also @Minecraft!

[Google DeepMind @GoogleDeepMind]

Four Gemini 4 Argon agents beat Minecraft from scratch in 27 hours.

Operating in a sandbox using only code and text, they wrote 2,783 programs, divided up jobs over chat, shared notes, and debugged errors together - all with no human help ↓
https://t.co/uyIhDOQXGT

[Zoubin Ghahramani @ZoubinGhahrama1]

Gemini 4 Argon agents in Minecraft collaborating, demonstrating remarkable long-term planning and problem-solving all the way to the end! Fascinating breakthrough. Congratulations to @maxencefaldor, @robertarail and Satinder Singh!

[Mikayel Samvelyan @_samvelyan]

Gemini 4 Argon agents are amazing and beat Minecraft in 27 hours ⛏️🤯

Fantastic work and report led by @maxencefaldor.

What a time to be alive. 🚀

[Uljad@NeurIPS @uljadb99]

A groundbreaking Frontier result!
@maxencefaldor and @robertarail did a phenomenal job in showing the Argon capabilities so effectively. What a model and what a team in every sense of the word!

[Roberta Raileanu @robertarail]

An independent research experiment, not an official Minecraft milestone, and not approved by or associated with Mojang or Microsoft. Visuals use the Pixel Perfection pack by XSSheep & Nova_Wostra (CC BY-SA 4.0).

[Roberta Raileanu @robertarail]

This year’s @stateofai is here! Thank you @nathanbenaich for the incredibly thorough synthesis and analysis, helping all of us make sense of the astonishing pace of progress in AI.

[Nathan Benaich @nathanbenaich]

welcome to the 9th annual @stateofai report!

ai building better ai, world models, physical ai, geopolitics, cyber defense and 12-month predictions.

read it at stateof(dot)ai or watch my editor’s cut here.

a few of this year’s biggest findings follow: