British Open-ended Learning and Discovery Lab

Come help us shape the future of AI research at BOLD!

Slight erratum… While we’re sure you all wish EGGROLL would be presented twice, one of these time slots was meant to read: ▶️ (✨✨Spotlight✨✨) Recurrent Structural Policy Gradient for Partially Observable Mean Field Games, Hall A #123, Wednesday 14:30-15:45, led by @ClarisseWibault

We hope you’ve enjoyed a sneak peek of work from BOLD and our collaborators at #ICML2026! See below for a full summary of where you can find us this week: ▶️ (Poster) Procedural Generation of Algorithm Discovery Tasks in Machine Learning, Hall A #1803, Tuesday 10:30 - 12:15, led by @AlexDGoldie ▶️ (Poster) h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning, Hall A #2704, led by Alesia Ivanova @sumeetrm ▶️ (Poster) Goal-Conditioned Agents that Learn Everything All at Once, Hall A #310, Tuesday 14:00 - 15:45, led by @mitrma ▶️ (Poster) Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Creative Writing, Hall A #2605, Wednesday 14:30 - 14:15, led by Tejas Krishnan @sumeetrm ▶️ (Poster) Evolution Strategies at the Hyperscale, Hall A #3712, Thursday 10:30 - 12:15, led by @bidiptas13 @JuanDuquevan Mattie Fellows ▶️ (Poster) Dreaming in Code for Curriculum Learning in Open-Ended Worlds, Hall A #213, Wednesday 17:00 - 18:45, led by @k_mitsides ▶️ (Poster) Evolution Strategies at the Hyperscale, Hall A #3712, Thursday 10:30 - 12:15, led by @bidiptas13 @JuanDuquevan Mattie Fellows ▶️ (Poster) The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind, Hall A #3504, Thursday 14:30 - 16:15, led by @_andreilupu ▶️ (Poster) LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning, Hall A #1705, Thursday 14:30 - 16:15, led by @sumeetrm @DanielNichols10 @CharlieLondon02 Peggy Li Fabio Pizzati ▶️ (Talk) Superhuman Scientific Discovery, RLxF Worskhop, Friday 15:30 - 16:00, by @robertarail ▶️ (Panel) RLxF Worskhop, Friday 16:00 - 17:00, by @robertarail ▶️ (Workshop) Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs, FoGen Workshop, Friday, led by @jakobhartmann99 James Harvey Jhonathan Navott ▶️ (Workshop) Elicitation Format Drives Divergent LLM Geopolitical Forecasts, AI Forecasting Workshop, Saturday, led by @hariharansuhas @michalbravansky ▶️ (Workshop) EGGROLL-IPO: Pluralistic Alignment via Decentralised Post-Training with Population Preferences, Pluralistic Alignment Workshop, Saturday, led by @alfie_lamerton ▶️ (Workshop Spotlight) Abstraction for Offline Goal-Conditioned Reinforcement Learning, DEMO Workshop, Saturday, led by @ClarisseWibault

Links (in order): DiscoGen: arxiv.org/pdf/2603.17863 h1: arxiv.org/pdf/2510.07312 LEO: arxiv.org/pdf/2605.23551 Rubric: openreview.net/pdf?id=LShWfvQ… RSPG: arxiv.org/pdf/2602.20141 EGGROLL: arxiv.org/pdf/2511.16652 DiCode: arxiv.org/pdf/2602.08194 Decrypto: arxiv.org/pdf/2506.20664 LongCOT: arxiv.org/pdf/2604.14140 Amortising: openreview.net/pdf?id=Yxu0uQu… Elicitation: openreview.net/pdf?id=G3F96WL… EGGROLL-IPO: openreview.net/pdf?id=5P7ihyD… ARL: arxiv.org/pdf/2605.22711

Another #ICML2026 BOLD paper, led by @bidiptas13, Mattie Fellows and @JuanDuquevan. We introduce EGGROLL, a novel general-purpose machine learning algorithm that provides a hundredfold increase in training speed over naïve evolution strategies. EGGROLL practically eliminates the barrier between inference and training, allowing us to easily fine-tune LLMs for reasoning or train new architectures from scratch. Check the paper at: arxiv.org/pdf/2511.16652

🚀 Three (yes, three!) papers on long-horizon reasoning and RL for non-verifiable domains from @sumeetrm, @CharlieLondon02, and collaborators at ICML 2026. h1 (Spotlight) trains models to reason over longer horizons using curriculum RL over composed short-horizon data. This allows models to generalize to harder tasks and improves performance even at high pass@k. LongCoT isolates and benchmarks long-horizon CoT capabilities, pushing models to reason well over tens and hundreds of thousands of tokens in an output. Rubric Curriculum RL uses the generation-verification gap in non-verifiable domains to allow models to self-improve on tasks like creative writing and health advicing. h1: arxiv.org/pdf/2510.07312 LongCoT: arxiv.org/abs/2604.14140 RcRL: openreview.net/pdf?id=LShWfvQ…

🧠 Our next #ICML2026 paper is a BOLD new benchmark, based on the game Decrypto, for LLM theory of mind led by @_andreilupu ! Taking inspiration from cognitive science, this work introduces a new multi-agent environment for LLMs and exposes systematic failures of frontier models when reasoning about the knowledge and beliefs of other agents. Check out the project page at: sites.google.com/view/decrypto-… And the paper: arxiv.org/pdf/2506.20664

❓Our next BOLD paper at #ICML2026 is led by @HarryMayne5 and @Justinkangs. A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior When LLMs explain their decisions, can we trust those explanations? We present a new metric based on whether explanations help predict a model’s behaviour on similar inputs. We find self-explanations encode value information about model decision making! Give the paper a read: arxiv.org/pdf/2602.02639

🔦 Another #ICML2026 paper from BOLD, and this time it's a SPOTLIGHT led by @ClarisseWibault. In this work, we introduce Recurrent Structural Policy Gradient for Partially Observable Mean-field Games with Common Noise. Our algorithm learns more realistic history-dependent behaviour, while also leveraging known structure to benefit from faster convergence than model-free RL methods! Check out the project page at: clarisse-wibault.github.io/rspg/, which includes links to our Mean-Field Game library, as well as a Google Colab example implementation! And the paper at: arxiv.org/pdf/2602.20141

🪩 Next #ICML2026 paper: DiscoGen, led by @AlexDGoldie. DiscoGen is a procedural generator of algorithm discovery problems for AI research agents, supporting the creation of over 100 billion diverse tasks! Tasks vary across many axes, such as their field of machine learning or datasets they use. They can even support different evaluations, such as the time an algorithm takes to train (speedrunning ⚡️), its energy usage (efficiency 🌱) or its performance 💪! Check out the paper at: arxiv.org/pdf/2603.17863 Give the code a look: github.com/AlexGoldie/dis… Or install the DiscoGen package for your research: pip install discogen

🛌💭Our next ICML paper is Dreaming in Code, led by @k_mitsides. In this work, LLMs are used as architects of experience: writing worlds in code that scaffold an RL agent towards long-horizon skills it could not discover alone! Check out the project page at: konstantinosmitsides.github.io/dreaming-in-co… And the paper: arxiv.org/pdf/2602.08194

The world doesn't wait for you to decide on an optimal action... but that's how we treat most RL research! Real-time RL learns how (and when) to plan - all while the environment is progressing in real-time. 👇 Check out our new paper!

Over this week, we'll be posting about papers from BOLD on show at the upcoming #ICML2026. Up first: LEO, led by @mitrma! Typical approaches in goal-conditioned RL select a single goal that is completed later in the episode. This paper instead asks a simple question: what if *every* goal is used for labelling (and how could we do that efficiently)? Check it out: arxiv.org/pdf/2605.23551

BOLD is brilliant from @KanishkaNarayan - just look at some of the things the founders have done 🧵

Very excited and honoured to launch BOLD! 3 universities, 6 co-leaders, outstanding researchers, all together with one goal: building a national AI Research Lab breaking discoveries in fundamental AI, toward open-ended learning, & open-source AI. Stay tuned!

🚨 2 major new AI labs in the UK 🚨 3 months ago, we launched a £40m call for a fundamental AI lab in the UK. Given the exceptional bids we received, we have doubled down: 2 new AI labs, £60m seed funding. ▪️@BOLD_LAB_AI: led by @j_foerst, with an exceptional team of @CULLYAntoine, @shimon8282, @tonizza82, Ani Calinescu & @_rockt ▪️SOFAIR: led by Prof David Barber, with a world-leading team of Mirella Lapata, @yaringal and @LourdesAgapito The best of UK academia, government and industry, together, to make fundamental advances in AI 🚀 researchprofessionalnews.com/rr-news-uk-pol…

It has been an absolute privilege and pleasure to build up @UCL_DARK with @egrefen, @robertarail and @jparkerholder over the past eight years. Yesterday, the UK government announced not just one but two national academic fundamental AI research labs. I am extremely excited to announce that @UCL_DARK will be sunsetted and merge with @FLAIR_Ox, @whi_rl, @UCL_LASP and AIRL, to form the British Open-ended Learning and Discovery (BOLD) Lab — @BOLD_Lab_AI. This is a huge moment for academic AI research in the UK. Backed with £30m by @UKRI_News and @EPSRC, it provides a unique opportunity to attract leading international academic talent to the UK, and equip them with the computational resources to do groundbreaking exploratory AI research (more on the computational resources soon). It also creates a mentorship network of academics, industry leaders and entrepreneurs to educate young talent on how to translate fundamental AI research into real world impact. I want to thank all the students who made @UCL_DARK successful, in particular our PhD alumni @MinqiJiang, @_samvelyan, @zhengyaojiang, @_robertkirk, @akbirkhan, @LauraRuis, @YingchenX, @PaglieriDavide, and the work of our honorary faculty @egrefen, @robertarail and @jparkerholder who were generously contributing to mentorship and research in their free time.

Very excited to launch BOLD 🚀 BOLD is a national shot at ambitious bluesky fundamental AI research in an academic setting, fully committed to open-source and open-science. BOLD's mission are research bets that would reshuffle the deck in AI if true. It will also be a launchpad for fast-tracking the British and European tech scene. Oh - and @FLAIR_Ox is no more.

Hello world :) We are BOLD — the British Open-ended Learning and Discovery Lab! BOLD is a new academic research lab fully focussed on paradigm breaking discoveries in fundamental AI. We work towards more efficient & open AI that is built around human needs and capabilities. To pursue these breakthroughs, we pioneer new modes of collaboration in academia that are more focussed, resourced, agile, and collaborative. Rather than fragmenting resources, today we are sunsetting 5 of the UKs leading AI labs to join forces under our joined scientific vision. Our vision is centered around three pillars: ⚡ Beyond backpropagation – questioning the foundations of the field. 🤝 Human-centric learning & discovery – treating humans as core to our algorithms 🤖 Embodied learning – fast learning and adapting methods that deal with the messy real world BOLD is backed by @UKRI_News and @EPSRC with £30M – and this is just the beginning. We are urgently looking for partners and sponsors to 10x this. 👉 ox.ac.uk/news/2026-06-2… 👉 bold-lab.ai @j_foerst, @CULLYAntoine, @tonizza82, @shimon8282, @tonizza82, Ani Calinescu & @_rockt