AI Paper Atlas

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

Can LLMs Reason Structurally? Benchmarking via the lens of Data Structures

Yu He, Yingxi Li, Colin White, Ellen Vitercik

ICML 2026 · Large language models › Agents, code and math · approach: Mathematical and structural reasoning benchmarks · 0 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
add CodeOnly (external interpreter) (ablation)GPT-4.1 · DSR-Bench code probescore: 0.40 -> 0.95Improved
add CodeOnly (external interpreter) (ablation)Claude-3.5-Sonnet · DSR-Bench code probescore: 0.44 -> 0.74Improved
add CodeOnly (external interpreter) (ablation)Gemini-2.0-Flash · DSR-Bench code probescore: 0.38 -> 0.44No clear effect
add CodeEnforce (write code, simulate internally) (ablation)GPT-4.1 · DSR-Bench code probescore: 0.40 -> 0.38No clear effect
add CodeMaybe (optional code) (ablation)o4-mini · DSR-Bench code probescore: 0.73 -> 0.76No clear effect
switch K-D heap tie-breaking from lexicographic order to Euclidean norm (ablation)o4-mini · DSR-Bench K-D Heapscore: drop of over 0.40Hurt
use reasoning models instead of instruction-tuned modelsDSR-Bench-main · DSR-Bench-mainoverall score: 0.79 -> 0.31Improved
add stepwise or 0-CoT prompts over None prompt (ablation)instruction-tuned models · DSR-Bench-mainscoreImproved
add well-designed CoT prompt on suffix tree (ablation)instruction-tuned models · DSR-Bench Suffix TreescoreImproved
move from formal to realistic narrative promptsLLMs · DSR-Bench realistic probescoreHurt
increase dimensionality of spatial data (k = 1, 2, 3, 5) (ablation)GPT-4.1 / o4-mini · DSR-Bench spatial probescoreHurt
use non-uniform data distributions (circles, moons, blobs) for K-D tree (ablation)GPT-4.1 · DSR-Bench spatial probescoreHurt

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