most citedEmbedded Universal Predictive Intelligence: a coherent framework for multi-agent learning

1 citations · 1 across the 6 of their papers we have counts for

collaborators

7 papers

cs.AI2026

A game theory for foundation models shows new paths to rational cooperation through similarity inference

Alexander Meulemans, Maciej Wołczyk, Marissa A. Weis +11

As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing their collective behavior is…

cs.NE2026

Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks

Ezekiel Williams, Alexandre Payeur, Guillaume Lajoie

Biological and neuromorphic recurrent neural networks (RNNs) are subject to spatial and temporal locality constraints on the information that can plausibly be used during learning.…

cs.LG2026

Beyond Distribution Sharpening: The Importance of Task Rewards

Sarthak Mittal, Leo Gagnon, Guillaume Lajoie

Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling system…

cs.LG2025

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel +12

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. Du…

cs.AI2025★ 1 cited

Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning

Alexander Meulemans, Rajai Nasser, Maciej Wołczyk +10

The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that polici…

cs.LG2025

Tracing the Representation Geometry of Language Models from Pretraining to Post-training

Melody Zixuan Li, Kumar Krishna Agrawal, Arna Ghosh +4

Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral approach to investigate the geometry of learn…