Foundations of Reasoning in Language Models

The workshop on Foundations of Reasoning in Language Models (FoRLM) will take place during the weekend of December 6-7 (TBD) at NeurIPS 2025 in San Diego, California.

Our workshop’s goal is to advance foundational understanding of reasoning in language models. Through theoretical analyses and rigorous empirical studies, we aim to illuminate how reasoning emerges, where it fails, and how it can be systematically improved.

We want to bring together researchers with complementary strengths—those building theoretical models of reasoning phenomena, those designing experiments that reveal its emergence or failure in practice, and those proposing algorithmic developments that advance reasoning—around three primary questions:

1. How are language models able to solve complex tasks, and what do they still struggle with?
2. What fundamental challenges stand in the way of advancing reasoning capabilities?
3. What algorithmic innovations can overcome these obstacles?

Submit: Please see our Call for papers for details and author instructions. The deadline is on Wednesday, September 3, 2025.