arXiv AI
Knowledge transfer between simple discrete worlds
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 12
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
arXiv:2604. 07822v2 Announce Type: replace-cross Abstract: We study implicit reasoning, i.
arXiv Machine Learning
Oct 8
The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning
The paper argues that pattern recognition and step‑by‑step reasoning lie on a spectrum, with large language models (LLMs) learning the latter when the next token depends on only a few preceding tokens. It formalises reasoning traces as paths on a De Bruijn graph, showing that the number of edges is far smaller than the number of possible traces, making step‑by‑step reasoning sample‑efficient. Experiments fine‑tuning Qwen2.5‑1.5B‑Instruct demonstrate that a moderate density of states balances accuracy and robustness, and that real‑world models like Qwen3 retain most of their performance even when attention is limited to a small sliding window.
arXiv AI
Sep 2
HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Models
arXiv:2609.00002v1 Announce Type: new Abstract: World models enable language-model agents to predict environment dynamics and plan before acting. In text environments, the model must learn symbolic a...
arXiv AI
Oct 1
What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling
arXiv:2609.39967v1 Announce Type: cross Abstract: Recursive reasoning models apply a small shared Transformer block many times to refine a latent state. This gives them large effective depth with few...
arXiv AI
Oct 15
Tiny Recursive Message Passing
Tiny Recursive Message Passing applies recursive transformers and deep supervision to message passing neural networks, achieving high efficiency. The approach yields about 99% test accuracy on Sudoku-Extreme with only 16k parameters, training quickly on modern GPUs or CPUs. It also demonstrates zero‑shot transfer to larger problem instances, outperforming popular neural baselines on N‑queens and Boolean satisfiability with fewer parameters.
arXiv AI
Oct 2
Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning
arXiv:2609.33149v2 Announce Type: replace Abstract: A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how...