arXiv Machine Learning August 17, 2026 By Giacomo Bocchese, Nicola Giacobbo, Etienne Guichard, James Wiles, Akshaj Devireddy

Emergent Models: Intelligence from Tiny Substrates

Read the original on arXiv Machine Learning →

arXiv:2608. 14019v1 Announce Type: cross Abstract: Emergent Models (EMs) are a machine learning paradigm based on simple yet open-ended substrates, such as cellular automata, in which modeling is treated not as the learning of a closed-form input-output map but as the emergence, within simple dynamical systems, of computational behaviors that solve external tasks.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

diffusion

arXiv Machine Learning

Jul 27

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.

By Shujin Wu, Cheng Qian, Xiusi Chen, Heng Ji

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 16

A Compositional Framework for Open-ended Intelligence

arXiv:2606. 15386v1 Announce Type: new Abstract: Open-ended intelligence is the capacity to adapt to novel problems and environments that are substantially different from those in training.

By Ida Momennejad, Roberta Raileanu

reinforcement-learning safety

arXiv AI

Jul 22

Intelligence from Learnable Novelty

arXiv:2607. 18433v1 Announce Type: cross Abstract: Intelligence appears under different names in different fields: as data compression in statistics and machine learning, as universal computation in dynamical systems, and as adaptive behavior in agents.

By Yanbo Zhang, Michael Levin

agents

arXiv AI

Jul 10

Architecture Generalization with MetaNCA

arXiv:2607. 07743v1 Announce Type: cross Abstract: Self-organization is an emergent property of life, driven by the collective behavior of individual components acting on local information.

By Meet Barot, Daniel Berenberg, Sina Khajehabdollahi

llms

arXiv Machine Learning

Jul 31

LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning

arXiv:2607. 28135v1 Announce Type: new Abstract: Machine learning for combinatorial optimization typically relies on neural constructors trained via reinforcement learning on large offline datasets for a fixed problem class-incurring high pretraining costs and generalizing poorly outside the training distribution.

By Mohand Mezmaz, Gr\'egoire Danoy

llms reinforcement-learning benchmarks

arXiv AI

Aug 12

SBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning Agents

arXiv:2608. 10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over time.

By Vivek Kulkarni, Sudipta Paul, Aounon Kumar, Nicholas Tzou, Srinivas Chappidi

agents safety

Related stories

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

A Compositional Framework for Open-ended Intelligence

Intelligence from Learnable Novelty

Architecture Generalization with MetaNCA

LM-GRASP: Instance-Specific Language Models for Combinatorial Construction via Online Imitation Learning

SBCO: Self-Supervised, Verifier-Grounded Harness Optimization For Planning Agents