LinearizeLLM: An Agent-Based Framework for LLM-Driven Exact Linear Reformulation of Nonlinear Optimization Problems
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
Reformulating nonlinear optimization problems into solver-ready linear optimization problems is often necessary for practical applications, but the process is often manual and requires domain expertise. We propose LinearizeLLM, an agent-based LLM framework that produces solver-ready linear reformulations of nonlinear optimization problems. Agents first detect the nonlinearity pattern (e.g., bilinear products) and apply nonlinearity pattern-aware reformulation techniques, selecting the most suitable linearization technique. We benchmark on 40 instances: 27 derived from ComplexOR by injecting exactly-linearizable operators, and 13 automatically generated instances with deeply nested nonlinearities. LinearizeLLM achieves 73% mean end-to-end overall success (OSR) across nonlinearity depths (8.3x higher than a one-shot LLM baseline; 4.3x higher than Pyomo). The results suggest that a set of pattern-specialized agents can automate linearization, supporting natural-language-based modeling of nonlinear optimization.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 7 of its 24 references that are in the map. First posted on arXiv 12 Oct 2025.
Builds on
7 of 24 references.
Closest ancestors · 1
Same direction, newest first
Other references · 6
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptionscited by 133
- 2024OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Modelscited by 105
- 2015Parallelizing the dual revised simplex methodcited by 83
- 2023Synthesizing mixed-integer linear programming models from natural language descriptionscited by 18
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation
- 2026A2utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction
- 2026Distribution-Aware Algorithm Design with LLM Agents
- 2026NC2C: Automated Convexification of Generic Non-Convex Optimization Problems
- 2026Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization
- 2026DRAGON: LLM-Driven Decomposition and Reconstruction Agents for Large-Scale Combinatorial Optimization
- 2025OptiMind: Teaching LLMs to Think Like Optimization Experts
- 2026From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling