A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction
Most LP-from-text benchmarks are static datasets of word problems written and labeled by hand. Once such a dataset is released, its size is fixed, its difficulty is fixed, and every problem can leak into the training data of future LLMs. We present \textbf{A$^{2}$utoLPBench}, a benchmark for testing LLM-driven agents on linear programming problems written in plain text. We first pick a feasible point and dual, then write down a problem for which that point is optimal and the objective value is known. The answer is known by construction, with no solver call and no human annotator. The evaluatio
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%run-llama/ParseBench →
- PossiblePossibly related (embedding) · 51%agent-tools →
- PossiblePossibly related (embedding) · 45%BoundaryML/baml →
- PossiblePossibly related (embedding) · 45%chrisliu298/awesome-llm-unlearning →
- PossiblePossibly related (embedding) · 50%Giskard-AI/giskard-oss →
- LinkedLinked via arxiv author · 85%Shuo Ren →
“A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction”
- LinkedLinked via arxiv author · 85%Yaohui Han →
“A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction”
- LinkedLinked via arxiv author · 85%Yifan Shi →
“A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction”