Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Meulemans, Alexander, Nasser, Rajai, Wołczyk, Maciej, Weis, Marissa A., Kobayashi, Seijin, Richards, Blake, Lajoie, Guillaume, Steger, Angelika, Hutter, Marcus, Manyika, James, Saurous, Rif A., Sacramento, João, Arcas, Blaise Agüera y
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence 68 I.2.6
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Multi-agent cooperation through in-context co-player inference
par: Weis, Marissa A., et autres
Publié: (2026)

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
par: Kobayashi, Seijin, et autres
Publié: (2025)

Multi-agent cooperation through learning-aware policy gradients
par: Meulemans, Alexander, et autres
Publié: (2024)

MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
par: von Oswald, Johannes, et autres
Publié: (2025)

Discovering modular solutions that generalize compositionally
par: Schug, Simon, et autres
Publié: (2023)

Learning Randomized Algorithms with Transformers
par: von Oswald, Johannes, et autres
Publié: (2024)

Gated recurrent neural networks discover attention
par: Zucchet, Nicolas, et autres
Publié: (2023)

Uncovering mesa-optimization algorithms in Transformers
par: von Oswald, Johannes, et autres
Publié: (2023)

The unreasonable effectiveness of pattern matching
par: Lupyan, Gary, et autres
Publié: (2026)

All Random Features Representations are Equivalent
par: Sernau, Luke, et autres
Publié: (2024)

Agentic AI and the next intelligence explosion
par: Evans, James, et autres
Publié: (2026)

When can transformers compositionally generalize in-context?
par: Kobayashi, Seijin, et autres
Publié: (2024)

State Soup: In-Context Skill Learning, Retrieval and Mixing
par: Pióro, Maciej, et autres
Publié: (2024)

What Lives? A meta-analysis of diverse opinions on the definition of life
par: Bender, Reed, et autres
Publié: (2025)

Attention as a Hypernetwork
par: Schug, Simon, et autres
Publié: (2024)

Towards a future space-based, highly scalable AI infrastructure system design
par: Arcas, Blaise Agüera y, et autres
Publié: (2025)

Reasoning Models Generate Societies of Thought
par: Kim, Junsol, et autres
Publié: (2026)

Can LLMs get help from other LLMs without revealing private information?
par: Hartmann, Florian, et autres
Publié: (2024)

Social Learning: Towards Collaborative Learning with Large Language Models
par: Mohtashami, Amirkeivan, et autres
Publié: (2023)

Synaptic Weight Distributions Depend on the Geometry of Plasticity
par: Pogodin, Roman, et autres
Publié: (2023)

Sufficient conditions for offline reactivation in recurrent neural networks
par: Krishna, Nanda H., et autres
Publié: (2025)

Scalable Spatiotemporal Prediction with Bayesian Neural Fields
par: Saad, Feras, et autres
Publié: (2024)

Robust Inverse Graphics via Probabilistic Inference
par: Le, Tuan Anh, et autres
Publié: (2024)

Weight decay induces low-rank attention layers
par: Kobayashi, Seijin, et autres
Publié: (2024)

Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models
par: Góral, Gracjan, et autres
Publié: (2024)

The challenge of hidden gifts in multi-agent reinforcement learning
par: Malenfant, Dane, et autres
Publié: (2025)

Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction
par: Arcas, Blaise Agüera y, et autres
Publié: (2024)

Multi-View Stochastic Block Models
par: Cohen-Addad, Vincent, et autres
Publié: (2024)

When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
par: Emmons, Scott, et autres
Publié: (2025)

Tracing the Representation Geometry of Language Models from Pretraining to Post-training
par: Li, Melody Zixuan, et autres
Publié: (2025)

Pushing Frontiers for Proteoglycans
par: Marissa L. Maciej‐Hulme
Publié: (2026)

Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty
par: George, Thomas, et autres
Publié: (2022)

Beyond Distribution Sharpening: The Importance of Task Rewards
par: Mittal, Sarthak, et autres
Publié: (2026)

Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks
par: Williams, Ezekiel, et autres
Publié: (2026)

Can LLMs make trade-offs involving stipulated pain and pleasure states?
par: Keeling, Geoff, et autres
Publié: (2024)

FlySearch: Exploring how vision-language models explore
par: Pardyl, Adam, et autres
Publié: (2025)

Beyond Recognition: Evaluating Visual Perspective Taking in Vision Language Models
par: Góral, Gracjan, et autres
Publié: (2025)

AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale
par: Pardyl, Adam, et autres
Publié: (2024)

Charge‐Mediated Interactions Affect Enzymatic Reactions in Peptide Condensates
par: Rif Harris, et autres
Publié: (2024)

Theory of Existing: The Metabolism of Reality Through Harmonic Processing
par: Steger, Cynthia
Publié: (2026)