EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
Summary
EvoOptiGraph is a framework for automating optimization modeling from natural language using graph-based evolutionary generation to create diverse training data and co-evolve the model with weakness-driven reinforcement learning, achieving state-of-the-art results on multiple benchmarks.
View Cached Full Text
Cached at: 06/26/26, 05:13 AM
# EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling Source: [https://arxiv.org/abs/2606.26578](https://arxiv.org/abs/2606.26578) [View PDF](https://arxiv.org/pdf/2606.26578) > Abstract:Automating optimization modeling from natural language with large language models \(LLMs\) faces two key challenges\. First, training corpora lack structural diversity\. Second, data generation pipelines remain static and decoupled from model learning\. To address these challenges, we propose EvoOptiGraph, a novel framework where data and model co\-evolve, driven by model weaknesses\. EvoOptiGraph represents each mixed\-integer linear program \(MILP\) as an attributed bipartite graph and applies validity\-preserving evolutionary operators to generate structurally diverse instances\. The evolved graphs are converted into solver code and natural language via deterministic compilation and verified back\-translation\. Training proceeds in two stages: supervised fine\-tuning \(SFT\) on an initial dataset, followed by reinforcement learning with verifiable rewards \(RLVR\), where graph\-derived weakness signals guide the generation of new instances targeting the model's failures\. This forms a closed loop that continuously updates the training distribution\. Empirical results on six public datasets show that EvoOptiGraph significantly outperforms larger generalist models, agentic methods, and specialized baselines in accuracy, executability, and generalization\. These results demonstrate that targeted data\-model coevolution is an effective strategy for improving LLMs on optimization modeling tasks\. ## Submission history From: Mingyang Liu \[[view email](https://arxiv.org/show-email/60d4af40/2606.26578)\] **\[v1\]**Thu, 25 Jun 2026 03:57:07 UTC \(3,473 KB\)
Similar Articles
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
MetaEvo proposes a two-stage framework for continual evolution of LLM-based agents, using preference-based optimization to enhance principle abstraction and modular architecture for experience reuse, outperforming strong baselines on reasoning benchmarks.
Interpreting Neural Combinatorial Optimization via Evolving Programmatic Bottlenecks
Introduces Evolving Programmatic Bottlenecks (EPB), a framework for interpreting neural combinatorial optimization policies by distilling black-box models into human-readable program portfolios using LLM-guided evolution.
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
Solvita is an agentic evolution framework that enables continuous learning in code generation through reinforcement learning updates to graph-structured knowledge networks, achieving state-of-the-art performance on competitive programming benchmarks.
Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation
Verilog-Evolve is a feedback-driven framework that iteratively refines Verilog code generated by large language models, using functional simulation, synthesis, and timing metrics to promote better candidates and evolve reusable repair skills across tasks.
EvoMap/evolver
Evolver is a GEP-powered self-evolution engine for AI agents that automates prompt optimization and creates auditable, reusable evolution assets. The project is transitioning from fully open source to source-available while maintaining backward compatibility with existing MIT and GPL-3.0 releases.