Roberta Raileanu

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

@deepaknathani11 @icmlconf Congrats Deepak!

Happy to be selected as a gold reviewer for ICML 2026, thanks to area chairs and @icmlconf Now I just need to get some money for flights 🇰🇷

@RichardSocher Congrats!!

@tydsh Congrats Yuandong!!

Today we launch Recursive. We are building AI that discovers knowledge automatically and improves itself recursively, an open-ended process that will fundamentally change how science and technology advance. Our 25 top researchers and engineers in San Francisco and London bring diverse expertise spanning agentic AI scientists, architecture and algorithm design, world models, optimization, and interpretability, united by a shared conviction that this is the most important problem we could be working on today. If you are interested in joining, please send your resume to talent@recursive.com. Follow us at @Recursive_SI!

@jeffclune Congrats Jeff, and best of luck!!

Thrilled to share that we founded Recursive to create AI that safely conducts experiments on how to improve itself in an open-ended process of endless, automated scientific discovery. As I wrote in my 2019 AI-generating algorithms paper, this will likely be the fastest path to superintelligence. Our work since has shown the power of this approach. Excited to scale up and improve upon ideas like the Darwin Gödel Machine, HyperAgents, ADAS, OMNI, ALMA, The AI Scientist, PromptBreeder, Rainbow Teaming, Automated Capability Discovery, and other work on open-ended and AI-generating algorithms. We’ve assembled a dream team of researchers and significant resources to pursue this vision. My amazing co-founders are pictured here, and we have an all-star team of founding members (we’re over 25 and growing). Please join us if you are interested! Follow our progress @Recursive_SI

@_rockt @Tim_Dettmers @Recursive_SI Very exciting, congrats Tim & team!!

Excited to co-found Recursive (@recursive_si) with an exceptional team in London and SF to create AI that experiments on how to safely improve itself, turning compute into knowledge that accumulates in an open-ended process of endless, automated scientific discoveries.

@shimon8282 @whi_rl Exciting, welcome to GDM!!

Major personal news: After 6 years, I am leaving Waymo to lead a new multi-agent learning team at DeepMind.

@deepaknathani11 Nice work bringing us one step closer to proactive assistants!

🎉 Excited to share 🍐 PARE and PARE-Bench - a framework and benchmark for evaluating proactive assistants through active user simulation in mobile environments. Current LM agents are reactive: they wait for you to tell them what to do. Proactive agents flip this. They observe what you're doing and figure out how to help. Imagine your assistant notices you got a text from your roommate saying "we're out of soap" while you're editing your shopping list, and adds soap to your list. 🚧 Evaluating these agents is challenging because they must observe realistic user behavior to infer goals. You can't do this with static benchmarks or passive users. Our key contributions: 🍐 PARE: an active user simulation framework where users navigate apps through Finite State Machine (FSM) based stateful interfaces, just like on a real phone 📱 Asymmetric design: users and assistants observe different information and interact through different interfaces, matching real-world deployment 👀 Observe-Execute architecture: lightweight observer monitors continuously, executor acts only after user approval 📋 PARE-Bench: 143 tasks across 9 app categories testing goal inference, intervention timing, and multi-app orchestration 📊 Evaluation of 7 LLMs reveals that even frontier models achieve only 42% success rate PARE is built on top of Meta's Agent Research Environment (ARE) and enables scalable, repeatable evaluation of proactive agents. In PARE, the simulated user goes about their day on the phone: accomplishing goals, navigating between apps, and responding to notifications. The proactive agent watches all of this unfold and uses the user's actions and environment signals to build context about what the user might need help with. Huge thanks to my advisors @xwang_lk @WilliamWangNLP and my amazing collaborators @JasonZ118707 @HuanCC2002 Jiaming Shan @yinfeiy Alkesh Patel @zhegan4 @m2saxon 🙏

@alex_peys Hopefully soon 🤞 it’s learning all the way down

@robertarail wen meta-meta-meta-meta learning?

How can agents get better at algorithm discovery? Meta-meta-learning is one answer, aka improving the agents themselves at inventing generalizable algorithms. DiscoBench provides a way to procedurally generate algorithm discovery tasks at scale, which can be used for meta-meta-learning. Kudos to @AlexDGoldie and team for the release!

@jennyzhangzt Congrats Jenny, this looks great!

Introducing Hyperagents: an AI system that not only improves at solving tasks, but also improves how it improves itself. The Darwin Gödel Machine (DGM) demonstrated that open-ended self-improvement is possible by iteratively generating and evaluating improved agents, yet it relies on a key assumption: that improvements in task performance (e.g., coding ability) translate into improvements in the self-improvement process itself. This alignment holds in coding, where both evaluation and modification are expressed in the same domain, but breaks down more generally. As a result, prior systems remain constrained by fixed, handcrafted meta-level procedures that do not themselves evolve. We introduce Hyperagents – self-referential agents that can modify both their task-solving behavior and the process that generates future improvements. This enables what we call metacognitive self-modification: learning not just to perform better, but to improve at improving. We instantiate this framework as DGM-Hyperagents (DGM-H), an extension of the DGM in which both task-solving behavior and the self-improvement procedure are editable and subject to evolution. Across diverse domains (coding, paper review, robotics reward design, and Olympiad-level math solution grading), hyperagents enable continuous performance improvements over time and outperform baselines without self-improvement or open-ended exploration, as well as prior self-improving systems (including DGM). DGM-H also improves the process by which new agents are generated (e.g. persistent memory, performance tracking), and these meta-level improvements transfer across domains and accumulate across runs. This work was done during my internship at Meta (@AIatMeta), in collaboration with Bingchen Zhao (@BingchenZhao), Wannan Yang (@winnieyangwn), Jakob Foerster (@j_foerst), Jeff Clune (@jeffclune), Minqi Jiang (@MinqiJiang), Sam Devlin (@smdvln), and Tatiana Shavrina (@rybolos).

ARC-AGI 3 is about to drop soon. Turns out games were a great benchmark for intelligence all along? 👀 While we wait, BALROG has got you covered. Here are some new exciting results for Gemini 3 Pro, Gemini 3.1 Pro, and Claude 4.5 Opus 🔥

Gemini 3.1 Pro has landed! Amazing performance / capabilities across the board. Beyond SOTA, the best are all the things that evals can't measure. E.g. SVG has gotten so much better (see 🧵) blog.google/innovation-and…

🧬 New paper from my internship at @GoogleDeepMind We introduce Persona Generators: functions that generate diverse synthetic populations for arbitrary contexts. We use AlphaEvolve to optimize the generator code, hill-climbing on diversity metrics — not just likelihood — counteracting the mode-seeking behavior of LLM sampling for agent-based simulations. 🧵👇1/

@iconicgamesio is really pushing the boundaries of what is possible with AI in games, and they are hiring!

Genie 3 can generate infinite worlds from just a single text or image prompt, and what's more, they are rich, interactive, and endlessly remixable. Project Genie: Available now for US Gemini Ultra subscribers. Enjoy! blog.google/innovation-and…

@_samvelyan @_rockt @borruell 🙏🙏🙏

An incredible PhD opportunity! 🚀 Working with @robertarail, @_rockt, and @borruell is an absolute dream. If you are applying this cycle, put this at the top of your list!

@CULLYAntoine 🙏🙏🙏

This is an outstanding PhD-opportunity if you are interested in open-endedness and video games! Check it out!

Great opportunity to do a PhD on Open-Ended Narrative Generation with @robertarail, @borruell, and myself in collaboration between @UCL_DARK and @iconicgamesio!