AI Paper Atlas

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

NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents

Yang Song, Anoushka Vyas, Zirui Wei, Sina Khoshfetrat Pakazad, Henrik Ohlsson, Graham Neubig

ICML 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 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 simulator-optimizer asymmetric validation (ablation)NEMO · BWORaccuracy: 71.9% -> 75.6%Improved
add simulator-optimizer asymmetric validation (ablation)NEMO · MAMO-Complexaccuracy: 50.9% -> 54.2%Improved
add simulator-optimizer asymmetric validation (ablation)NEMO · IndustryORaccuracy: 60.0% -> 60.0%No clear effect
add external memory of retrieved OptMATH examples (ablation)NEMO Base · MAMO-Complexaccuracy: 54.2% -> 61.9%Improved
add external memory of retrieved OptMATH examples (ablation)NEMO Base · BWORaccuracy: 75.6% -> 80.4%Improved
add component-wise MBR decoding with LLM re-ranking (ablation)NEMO +Mem · MAMO-Complexaccuracy: 61.9% -> 71.0%Improved
add multiple optimizer backends and self-consistency (ablation)NEMO +Mem+MBR · BWORaccuracy: 80.4% -> 82.9%Improved
add multiple optimizer backends (ablation)NEMO +Mem+MBR · IndustryORaccuracy: 63.0% -> 63.0%No clear effect
use NEMO instead of compute-matched Best-of-5 ACAClaude 4.5 Sonnet ACA · BWORaccuracy: 79.3% -> 86.6%Improved
use NEMO instead of compute-matched Best-of-5 ACAClaude 4.5 Sonnet ACA · OptMATH-Benchaccuracy: 62.7% -> 68.1%Improved
add simulator on top of full pipeline (ablation)NEMO (Claude 4.5 Sonnet) · BWORaccuracy: 80.5% -> 86.6%Improved

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