Reasoning · Evaluation

Mathematical LLMs Survey

First page

Paper summary

A survey on the progress of LLMs on mathematical reasoning tasks, covering methods, benchmarks, and open problems.

Ask this paper

Key points

Task taxonomy: Covers math word problem solving, symbolic reasoning, and theorem proving, showing which capabilities emerge at which model scales.

Methods landscape: Reviews prompting techniques (CoT, PoT, ToT, self-verification) alongside fine-tuning and tool-use approaches.

Dataset reference: Catalogs the dominant math benchmarks (GSM8K, MATH, MiniF2F, etc.) and their evaluation methodologies.

Frontier problems: Highlights reasoning-faithfulness, formal-vs-informal math integration, and reward-model design as the key open questions.

Every Monday