Learning to reason with LLMs

Jupyter Agents: training LLMs to reason with notebooks

SmolLM3: smol, multilingual, long-context reasoner

Controlling Reasoning Effort in LLMs

How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes

How reliable are LLMs when it comes to playing dice?

arXiv:2606. 07515v1 Announce Type: cross Abstract: We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems.

Categories of Inference-Time Scaling for Improved LLM Reasoning

And an Overview of Recent Inference-Scaling Papers

Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures

arXiv:2505. 24069v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are deployed on increasingly complex tasks that require multi-step decision-making.