Author

Jungang Xu

h-index 1 View on Semantic Scholar

We have 2 of 8 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

ModelEquivBench: Certifying Multi-Relational Evaluation of LLM-Generated Optimization Models

ModelEquivBench is presented, a certifying, multi-relational evaluation system that reports a per-pair semantic profile E0--E6 that contains relation-appropriate, independently re-checkable evidence: replayable traces or explicit maps for E0--E1, exact-rational certificates for positive E2--E6 conclusions, and explicit...

Penglin Zhu, Jungang Xu · arXiv.org · 0 citations

Preprint Jul 2026

IR2Solve: Structured Intermediate Representations for Cost-Efficient Optimization Autoformulation

Large language models (LLMs) can translate natural-language optimization problems into solver-ready formulations, but direct code generation is brittle: schema, indexing, and semantic errors can cause compilation failures, infeasible models, or incorrect objectives, while iterative repair, search, and multi-agent workf...

Penglin Zhu, Linhai Zhang, Jungang Xu et al. · 0 citations