NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents

TL;DR

NEMO is a system that converts natural language descriptions into executable optimization code using autonomous coding agents, enabling validation, repair, and high performance on benchmarks.

Contribution

NEMO introduces autonomous coding agents and novel coordination patterns for reliable, execution-aware optimization modeling from natural language descriptions.

Findings

Achieves state-of-the-art results on nine optimization benchmarks.

Demonstrates robustness through validation loops and self-consistency.

Enables automated validation and repair of generated code.

Abstract

In this paper, we present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implementations, operating collaboratively with users or autonomously. Existing approaches typically rely on specialized large language models (LLMs) or bespoke, task-specific agents. Such methods are often brittle, complex and frequently generating syntactically invalid or non-executable code. NEMO instead centers on remote interaction with autonomous coding agents (ACAs), treated as a first-class abstraction analogous to API-based interaction with LLMs. This design enables the construction of higher-level systems around ACAs that structure, consolidate, and iteratively refine task specifications. Because ACAs execute within sandboxed environments, code produced by NEMO is executable by construction, allowing automated validation and repair. Building on this, we introduce novel coordination patterns with and across ACAs, including asymmetric validation loops between independently generated optimizer and simulator implementations (serving as a high-level validation mechanism), external memory for experience reuse, and robustness enhancements via minimum Bayes risk (MBR) decoding and self-consistency. We evaluate NEMO on nine established optimization benchmarks. As depicted in Figure 1, it achieves state-of-the-art performance on the majority of tasks, with substantial margins on several datasets, demonstrating the power of execution-aware agentic architectures for automated optimization modeling.