114 citations · 353 across the 89 of their papers we have counts for
92 papers
Understanding the Inner Workings of a State-Space Foundation Model for Limit Order Books
Valentin Mohl, Alexandre Bismuth, Aramis Marti-Shahandeh +6
Autoregressive foundation models offer state-of-the-art capabilities to simulate the market by generating the message flow of limit order books (LOBs). Yet, without understanding t…
20,000 Rotation Periods in Nearby Open Clusters and Moving Groups from ZTF and ASAS-SN
Yuxi Lu
Open clusters provide uniquely powerful laboratories for studying stellar evolution because their members share a common age and chemical composition. Stellar rotation of low-mass…
GitSwarm: Decentralized Compounding Inference
Vedant Shah, Ankur Samanta, Paras Dahal +11
Long-horizon problem solving and scientific research require computation to accumulate across successive attempts. Partial solutions, experimental findings, and unsuccessful approa…
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty +3
We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single ep…
AI Research Preference Models
Thomas Simon Foster, Bassel Al Omari, Tingchen Fu +30
AI research agents (AIRA) can now carry machine learning experiments from proposal through implementation and evaluation. Yet progress on frontier tasks is throttled by the cost of…
Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details
Maksymilian Wolski, Nicholas Hoernle, Johannes Forkel +1
AI agents deployed in real-world settings must be capable of coordinating with humans and other AI agents they have not encountered before. Zero-shot coordination (ZSC) algorithms…
Autodata: An agentic data scientist to create high quality synthetic data
Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu +12
We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show how to train (meta-optimize) s…
Inverting the Bellman Equation: From -Values to World Models
Alistair Letcher, Mattie Fellows, Alexander D. Goldie +3
Model-based and model-free reinforcement learning are traditionally viewed as separate paradigms: instead of learning a model of the transition kernel , model-free agents typica…
Modelling Opinion Dynamics at Scale with Deep MARL
Lukas Seier, Brandon Kaplowitz, Sebastian Towers +2
Modelling opinion dynamics typically relies on hand-crafted local interaction rules to study emergent macroscopic phenomena such as consensus and polarisation. In contrast, multi-a…
Towards End-to-End Automation of AI Research
Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5
The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific pr…
Goal-Conditioned Agents that Learn Everything All at Once
Michael Matthews, Matthew Jackson, Michael Beukman +5
A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing o…
Abstraction for Offline Goal-Conditioned Reinforcement Learning
Clarisse Wibault, Alexander Goldie, Antonio Villares +2
Markov Decision Processes (MDPs) often exhibit significant redundancy due to symmetries and shared structure across state-goal pairs in real-world Goal-Conditioned Reinforcement Le…
JAX-Based Batched AC Power Flow for GPU Acceleration and AI Ecosystem Integration
Yihong Zhou, Dylan Cope, Jakob Foerster +1
Coordinating growing grid flexibility under uncertainty is becoming increasingly important for efficient and reliable power-system operation. A core computational requirement is th…
Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training
Uljad Berdica, Jakob Foerster, Frank Hutter +1
The generation of sustained, open-ended complexity from local interactions remains a fundamental challenge in artificial life. Differentiable multi-agent systems, such as Petri Dis…
Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews
Shreyansh Padarha, Ryan Othniel Kearns, Tristan Naidoo +13
Systematic literature reviews (SLRs) are a demanding and high-stakes form of scientific knowledge synthesis that remains underspecified as an evaluation setting for large language…
DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning
Alexander D. Goldie, Zilin Wang, Adrian Hayler +17
Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and evaluate algorithm discovery systems ha…
Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic Verification
Erik Y. Wang, Sumeet R. Motwani, James V. Roggeveen +9
Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientific reasoning, but whether they ca…
Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments
Michael Beukman, Khimya Khetarpal, Zeyu Zheng +4
An agent's performance stagnating at a suboptimal level is a common problem in deep on-policy RL. Focusing on PPO, we show that plateaus in certain regimes arise not because of kno…
Recurrent Structural Policy Gradient for Partially Observable Mean Field Games
Clarisse Wibault, Johannes Forkel, Sebastian Towers +9
Mean Field Games (MFGs) provide a principled framework for modelling interactions in large population systems. However, algorithmic progress has been limited since model-free metho…
Asking the Right Questions: Improving Reasoning with Generated Stepping Stones
Hengyuan Hu, Tingchen Fu, Minqi Jiang +3
Recent years have witnessed tremendous progress in enabling LLMs to solve complex reasoning tasks such as math and coding. As we start to apply LLMs to harder tasks that they may n…
High entropy leads to symmetry-equivariant policies in Dec-POMDPs
Johannes Forkel, Constantin Ruhdorfer, Michael Beukman +2
We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initia…
The Yokai Learning Environment: Tracking Beliefs Over Space and Time
Constantin Ruhdorfer, Matteo Bortoletto, Johannes Forkel +2
The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm…
Fully Offline Reinforcement Learning
Mattie Fellows, Clarisse Wibault, Uljad Berdica +3
Offline RL (ORL) promises safe and sample-efficient deployment but existing methods rely on undocumented online interactions for hyperparameter tuning and lack reliable fully offli…
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5
AI is increasingly playing a pivotal role in transforming how scientific discoveries are made. We introduce The AI Scientist-v2, an end-to-end agentic system capable of producing t…