arXiv AI June 19, 2026 By Yanhong Li, Anej Svete, Ashish Sabharwal, William Merrill

Efficiently Representing Algorithms With Chain-of-Thought Transformers

arXiv:2606. 19697v1 Announce Type: cross Abstract: The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation.

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

llms

arXiv Machine Learning

Jun 3

Why Are Linear RNNs More Parallelizable?

arXiv:2603. 03612v3 Announce Type: replace Abstract: The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability.

By William Merrill, Hongjian Jiang, Yanhong Li, Anthony Lin, Ashish Sabharwal

llms

arXiv Machine Learning

Aug 10

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought

arXiv:2605. 18079v2 Announce Type: replace Abstract: Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice.

By Moritz Br\"osamle, Stephan Eckstein

llms safety

arXiv Machine Learning

Aug 11

Barriers to Universal Reasoning With Transformers (And How to Overcome Them)

arXiv:2604. 25800v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing completeness.

By Oliver Kraus, Yash Sarrof, Yuekun Yao, Alexander Koller, Michael Hahn

llms

Hugging Face Trending Papers

Aug 4

Separating quantum circuits from classical LLMs

Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation. We prove unconditional separations between low-depth quantum computation and the corresponding bounded-resource classical language-model architectures in both regimes.

llms diffusion

arXiv AI

Aug 5

Separating quantum circuits from classical LLMs

arXiv:2608. 03962v1 Announce Type: cross Abstract: Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation.

By Srinivasan Arunachalam, Arkopal Dutt, Hari Krovi, Rik Sengupta

llms diffusion

arXiv AI

Jun 9

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels

arXiv:2606. 07713v1 Announce Type: cross Abstract: The attention mechanism is the dominant computational bottleneck in modern transformer-based AI.

By Lenore Mullin, Gaetan Hains

llms

Related stories

Why Are Linear RNNs More Parallelizable?

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought

Barriers to Universal Reasoning With Transformers (And How to Overcome Them)

Separating quantum circuits from classical LLMs

Separating quantum circuits from classical LLMs

Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optimal Transformer Kernels