A Measure-Theoretic Analysis of Reasoning in Transformers: Structural Generalization and Approximation Limits

arXiv:2605.19944 · cs.LG, cs.AI, cs.CC, cs.CL · Submitted 2026-05-19 · Read on arXiv

cs.LG, cs.AI, cs.CC, cs.CL

Submitted: 2026-05-19

Updated: 2026-10-19

Comments: Accepted at NeurIPS 2026. v2: camera-ready version. 54 pages (10-page main text), 6 figures, 3 tables. Code and results: https://github.com/Yyuzrah/AMTA4R

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 4× in this paper · explained in 13 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Domain Shift — 2× in this paper · explained in 6 episodes
• Transformers — 2× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Equivariance — 1× in this paper · explained in 2 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks