AI Paper Atlas

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

VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification

Sumaya Abdul Rahman, Seckhen Ariel Andrade Cuellar, Ghani Raissov, Mohammad Raza

ICML 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 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 simplification-based verification and candidate selection to the base LLMGPT-4o · average over 4 optimization benchmarksaccuracy: 56.6 -> 65.5Improved
add simplification-based verification to the base LLMDeepSeek-R1 · average over 4 optimization benchmarksaccuracy: 62.5 -> 72.8Improved
use VeriSimpl instead of OptiMUS multi-agent pipelineGPT-4o · IndORaccuracy: 17.7 -> 45.8Improved
add full-variable verification, single-variable, and type verification to constraint verification (full VeriSimpl vs A-Cons) (ablation)VeriSimpl · average accuracy, GPT-4oaccuracy: 63.9 -> 65.5Improved
add all verification signals vs only full-variable verification (ablation)VeriSimpl · average accuracy, GPT-4oaccuracy: 62.2 -> 65.5Improved
add the other verification signals to singleton-variable verification (ablation)VeriSimpl · average accuracy, DeepSeek-R1accuracy: 68.9 -> 72.5Improved
add type-based verification and refinement (ablation)VeriSimpl · average accuracy, DeepSeek-R1accuracy: 72.3 -> 72.5No clear effect
add type-based verification and refinement (ablation)VeriSimpl · average accuracy, GPT-4oaccuracy: 64.2 -> 65.5Improved
require all verification queries to pass (full self-verification) as a confidence signalVeriSimpl · average over datasets, GPT-4oprecision: 65.5 accuracy -> 91.5 precision (coverage 34.2)Improved
use R1 instead of GPT-4o as the base for self-verificationVeriSimpl · average over datasetsprecision: 91.5 -> 78.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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