Probabilistic Results on the Architecture of Mathematical Reasoning Aligned by Cognitive Alternation
On the map: LLM reasoning → Mathematical reasoning
Abstract (arXiv)
We envision a machine capable of solving mathematical problems. Dividing the quantitative reasoning system into two parts: thought processes and cognitive processes, we provide probabilistic descriptions of the architecture.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 1 of its 18 references that are in the map. First posted on arXiv 17 Aug 2023.
Builds on
1 of 18 references.
Closest ancestors · 1
Same direction, newest first
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges
- 2025Systematic Diagnosis of Brittle Reasoning in Large Language Models
- 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery
- 2025Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
- 2025Thinking Machines: Mathematical Reasoning in the Age of LLMs
- 2024Large Language Models for Mathematical Reasoning: Progresses and Challenges
- 2024Inference of Abstraction for a Unified Account of Symbolic Reasoning from Data
- 2026Hypothesis-guided discovery of cognitive algorithms via program refinement