AI Paper Atlas

Research map / Large language models / Agents, code and math

Benchmarking LLMs’ Mathematical Reasoning with Unseen Random Variables Questions

Zijin Hong, Hao Wu, Su Dong, Junnan Dong, Yilin Xiao, Yujing Zhang, Zhu Wang, Feiran Huang, Linyi Li, Hongxia Yang, Xiao Huang

AAAI 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace fixed-variable original problems with random-variable questionsLLMs on MATH · MATH-SP -> MATH-RVaccuracy: GPT-4o 83.48 -> 76.70; Llama-3.1-8B-It 57.39 -> 46.43Hurt
replace original LeetCode-Math problems with random-variable questionsLLMs on LeetCode-Math · LeetCode-SP -> LeetCode-RVaccuracy: GPT-4o 61.74 -> 50.09Hurt
apply test-time scaling (pass@10 vs single attempt) (ablation)Llama-3.2-3B-It · LeetCode-RVaccuracy: 26.67% -> 56.52%Improved
use stronger models (higher MATH-RV accuracy)LLMs · MATH-RV robustnessaccuracy drop: Pearson r = -0.72Improved
higher LeetCode-RV accuracy vs robustnessLLMs · LeetCode-RV robustnessaccuracy drop: Pearson r = -0.14No clear effect
use reasoning models (o3-mini, DeepSeek-R1) vs chat LLMs like GPT-4oRV-Bench · RV-Bench overallaccuracy: 85.05 / 82.35 vs 63.40Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy