arXiv Machine Learning July 3, 2026 By Aria Masoomi, Mahsa Bazzaz, Adel Javanmard, Vahab Mirrokni

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

Read the original on arXiv Machine Learning →

arXiv:2607. 01571v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by generating intermediate reasoning steps.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Sep 1

SHAPE of Chain-of-Thought in Math Reasoning

arXiv:2608.28600v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance on mathematical reasoning benchmarks, yet the mathematically meaningful skills underlying their...

By Jonghyun Song, Sangjun Song, Minjae Oh, Haesung Pyun, Sungsik Lee, Yohan Jo

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 5

Reasoning Models Don't Just Think Longer, They Move Differently

arXiv:2605. 15454v2 Announce Type: replace-cross Abstract: Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computing for more steps or following a different internal trajectory.

By Anders Gj{\o}lbye, Lars Kai Hansen, Sanmi Koyejo

llms

arXiv AI

Aug 10

Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking

arXiv:2608. 07077v1 Announce Type: new Abstract: The Tower of Hanoi is a simple planning puzzle that in prior work has proven challenging for large reasoning models (LRMs).

By Devin Pereira, Willem Zuidema

llms safety

arXiv AI

Aug 5

The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics

arXiv:2608. 03291v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process.

By Shashwat Sourav, Aishwarya Balwani

llms

arXiv AI

Sep 16

State of Thought Enables Endogenous Reasoning

arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasonin...

By Zhiren Gong, Yikun Hou, Zihao Zeng, Ming Xiao, Chau Yuen, Wei Yang Bryan Lim

llms rag multimodal

arXiv AI

Jun 15

Fractured Chain-of-Thought Reasoning

arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.

By Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong

llms benchmarks

One email a morning, machine-written

Related stories

SHAPE of Chain-of-Thought in Math Reasoning

Reasoning Models Don't Just Think Longer, They Move Differently

Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking

The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics

State of Thought Enables Endogenous Reasoning

Fractured Chain-of-Thought Reasoning