OPT-Engine shows pure-text chain-of-thought reasoning in LLMs loses robustness as optimization complexity grows, external tools fix only local arithmetic, and solver-integrated methods are bottlenecked by automated constraint formulation.
InProceedings of the 41st International Conference on Machine Learning, pages 577–596
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
APF automates solver-independent formulation of optimization problems from natural language via LLMs fine-tuned on synthetically generated high-quality data, outperforming prior methods on antenna radiation efficiency tasks.
MiniOpt trains LLMs under 10B parameters via RL with OptReward to model and solve general optimization problems, reporting highest average solving accuracy among comparable models.
citing papers explorer
-
OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling
OPT-Engine shows pure-text chain-of-thought reasoning in LLMs loses robustness as optimization complexity grows, external tools fix only local arithmetic, and solver-integrated methods are bottlenecked by automated constraint formulation.
-
Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design
APF automates solver-independent formulation of optimization problems from natural language via LLMs fine-tuned on synthetically generated high-quality data, outperforming prior methods on antenna radiation efficiency tasks.
-
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
MiniOpt trains LLMs under 10B parameters via RL with OptReward to model and solve general optimization problems, reporting highest average solving accuracy among comparable models.