Opti-Agent-Bench: Benchmarking End-to-End Optimization R&D Agents on Real-World Business Problems

📅 2026-07-12
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing benchmarks struggle to evaluate the ability of large language models to perform end-to-end optimization tasks in real-world business settings. This work proposes the first comprehensive end-to-end evaluation benchmark that spans business requirement interpretation, mathematical modeling, algorithm selection, code implementation, and report generation. It introduces three key innovations: business-semantic anti-template traps, cross-module consistency checks, and a dual-layer ORAC validity verification framework, covering core optimization paradigms such as integer programming, robust optimization, stochastic programming, and non-convex optimization. Experiments reveal systematic deficiencies in current models—including omitted constraints and inconsistencies between formulated models and generated code—that remain undetected under conventional single-metric evaluations, thereby demonstrating the necessity and effectiveness of this benchmark for assessing complex, multi-stage optimization workflows.
📝 Abstract
LLM-based agents are increasingly deployed to solve optimization problems, yet existing benchmarks evaluate them on pre-structured mathematical formulations that bypass the most critical challenge: translating complex business requirements into correct models and solve efficiently. We introduce Opti-Agent-Bench, an end-to-end benchmark that evaluates Large Language Models (LLMs) across the complete optimization R&D pipeline, from understanding business-language descriptions through mathematical modeling, algorithm selection, and code implementation, to solution report generation. Our design rests on three pillars: (1) businesssemantic authenticity with anti-template traps that defeat pattern matching; (2) modular evaluation with cross-module consistency checking across Problem Understanding, Formal Modeling, Implementation, and Reporting; and (3) the ORAC bi-level validity framework that simultaneously ensures task quality and scoring integrity. Across several industrialscale tasks spanning integer programming, robust optimization, stochastic programming, and non-convex optimization, we expose critical failure modes of current models, including constraint omission, model-code inconsistency, and report-implementation divergence, that remain invisible under conventional single-metric evaluation.
Problem

Research questions and friction points this paper is trying to address.

optimization agents
business-to-model translation
end-to-end benchmarking
large language models
real-world optimization
Innovation

Methods, ideas, or system contributions that make the work stand out.

Opti-Agent-Bench
end-to-end optimization
business-semantic authenticity
modular evaluation
ORAC framework
🔎 Similar Papers
No similar papers found.
Y
Yongchang Fu
Ding Talk, Alibaba Group, Hangzhou, China
X
Xinjie Huang
Ding Talk, Alibaba Group, Hangzhou, China; Zhejiang University, Hangzhou, China
C
Chengjun Dai
Ding Talk, Alibaba Group, Hangzhou, China
C
Chengzhe Feng
Ding Talk, Alibaba Group, Hangzhou, China
J
Junshao Zhang
Ding Talk, Alibaba Group, Hangzhou, China
H
Hong Zhu
Ding Talk, Alibaba Group, Hangzhou, China