ReLoop closes the feasibility-correctness gap in LLM optimization code via structured generation and behavioral verification with parameter perturbations, reaching 100% executability and accuracy gains on benchmarks while releasing RetailOpt-190.
Mamo: a mathematical modeling benchmark with solvers
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 5representative citing papers
LLMs prompted with domain knowledge can generate runnable, numerically valid code for stiff and non-stiff ODEs on new diagnostic and 1000-task benchmarks.
PARM adapts reward models to multi-stage LLM pipelines via pipeline data and direct preference optimization, improving execution rate and solving accuracy on optimization benchmarks and showing transfer to GSM8K.
EvoOR-Agent co-evolves agent architectures as AOE-style networks with graph-mediated recombination and knowledge-base-assisted mutation to outperform fixed LLM pipelines on OR benchmarks.
AutoOR uses synthetic data generation and RL post-training with solver feedback to enable 8B LLMs to autoformalize linear, mixed-integer, and non-linear OR problems, matching larger models on benchmarks.
citing papers explorer
-
ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
ReLoop closes the feasibility-correctness gap in LLM optimization code via structured generation and behavioral verification with parameter perturbations, reaching 100% executability and accuracy gains on benchmarks while releasing RetailOpt-190.
-
SciML Agents: Write the Solver, Not the Solution
LLMs prompted with domain knowledge can generate runnable, numerically valid code for stiff and non-stiff ODEs on new diagnostic and 1000-task benchmarks.
-
PARM: Pipeline-Adapted Reward Model
PARM adapts reward models to multi-stage LLM pipelines via pipeline data and direct preference optimization, improving execution rate and solving accuracy on optimization benchmarks and showing transfer to GSM8K.
-
Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
EvoOR-Agent co-evolves agent architectures as AOE-style networks with graph-mediated recombination and knowledge-base-assisted mutation to outperform fixed LLM pipelines on OR benchmarks.
-
AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems
AutoOR uses synthetic data generation and RL post-training with solver feedback to enable 8B LLMs to autoformalize linear, mixed-integer, and non-linear OR problems, matching larger models on benchmarks.