arXiv AI

Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions

The paper introduces SDDL, a neuro‑symbolic framework that converts natural‑language combinatorial scheduling problems into compact, solver‑aligned representations, delegating low‑level modeling and search to a deterministic compiler and external solver. On a 300‑instance subset of scheduling tasks, SDDL achieves higher feasibility rates for resource‑constrained language models—up to 55.3% and 28.3%—compared to direct‑generation baselines (23.7% and 1.3%) and solver‑code baselines (21.7% and 7.0%), with a median optimality gap of 0.0% among feasible schedules.

arXiv Computation and Language

Aug 27

SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling

SCHEDBench is a natural‑language benchmark that evaluates whether large language models (LLMs) produce schedules that remain constraint‑feasible when the same scheduling problem is expressed in different natural‑language surface forms. The benchmark covers 1,132 instances from job‑shop scheduling, resource‑constrained project scheduling, nurse rostering, and curriculum timetabling, and uses domain‑specific templates and surface‑form variations to generate varied problem statements. Experiments with thirteen frontier and open‑weight LLMs show that models are not reliably invariant to semantically equivalent renderings, with surface‑form variation reducing feasibility and increasing hard‑constraint violations, especially when constraints are reordered.

By Shrenil Shaun Sharma, Avi Sharma

llms benchmarks

arXiv AI

Oct 19

LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization

LangNCO is a framework that transforms natural-language constraints into structured inference-time interventions for a frozen neural combinatorial optimization (NCO) solver. It uses a pretrained large language model to convert each requirement into a domain-specific language rule set, which a deterministic Rule Executor applies as hard action masks. Critical-Offset Decoding then reallocates rollout budget to ensure feasibility, achieving near-perfect feasibility across multiple constraint types without retraining the solver.

By Hironori Ohigashi

llms

arXiv AI

Aug 5

IR2Solve: Structured Intermediate Representations for Cost-Efficient Optimization Autoformulation

arXiv:2608. 02641v1 Announce Type: cross Abstract: 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 workflows increase inference cost.

By Penglin Zhu, Linhai Zhang, Jungang Xu, Xinchi Wei, Xiuqi Wu

llms agents benchmarks

arXiv AI

Jun 16

Large Language Models as Optimizers: A Survey of Direct vs. Tool-Augmented Approaches and Their Performance Frontiers

arXiv:2606. 15577v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly involved in complex mathematical optimization, even if the pragmatic user who triggers them is unaware of it.

By Roko Peran, Luka Hobor, Mihael Kovac, Mario Brcic

llms benchmarks

arXiv AI

Jun 4

Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems

arXiv:2606. 04816v1 Announce Type: new Abstract: Large language models (LLMs) increasingly translate natural-language optimization problems into executable solver code.

By Xizi Luo, Changhong He, Dongdong Geng, Chenggong Shi, Yu Mei

llms benchmarks

arXiv AI

Jul 7

Programming over Thinking: Efficient and Robust Multi-Constraint Planning

arXiv:2601. 09097v3 Announce Type: replace Abstract: Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constraints.

By Derrick Goh Xin Deik, Quanyu Long, Zhengyuan Liu, Nancy F. Chen, Wenya Wang

llms benchmarks

arXiv AI

Aug 10

Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling

arXiv:2608. 07040v1 Announce Type: new Abstract: Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations.

By Shaofeng Zhang, Hongyuan Su, Qingwen Peng, Zefang Zong, Shengcai Liu, Ke Tang, Yong Li

llms benchmarks

arXiv AI

Jun 16

A Learning Method with Gap-Aware Generation for Heterogeneous DAG Scheduling

arXiv:2603. 23249v2 Announce Type: replace-cross Abstract: Efficient scheduling of directed acyclic graphs (DAGs) is a core problem in large-scale data-intensive computing systems, where query plans, data-processing workloads, and computation graphs consist of dependent tasks competing for limited heterogeneous resource pools.

By Ruisong Zhou, Haijun Zou, Li Zhou, Chumin Sun, Zaiwen Wen

reinforcement-learning

arXiv AI

Jun 30

OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale

arXiv:2407. 19633v4 Announce Type: replace Abstract: Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare.

By Ali AhmadiTeshnizi, Wenzhi Gao, Herman Brunborg, Shayan Talaei, Connor Lawless, Madeleine Udell

llms fine-tuning benchmarks

arXiv AI

Jul 24

VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification

arXiv:2607. 20474v1 Announce Type: new Abstract: Natural language interfaces can greatly benefit the accessibility and usability of optimization modeling, and recent advances in large language models (LLMs) show promise in automatically translating textual problem descriptions into executable solver formulations.

By Sumaya Abdul Rahman, Seckhen Ariel Andrade Cuellar, Ghani Raissov, Mohammad Raza

llms benchmarks

arXiv Computation and Language

Oct 15

BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla

BANGLAPLAN is a new benchmark comprising 1,000 Bangla planning and decision‑making problems across ten everyday task families, presented in four language registers (everyday, formal, colloquial, and Bangla–English mixed). The benchmark includes both feasible and infeasible instances and requires answers in eight structured JSON formats such as schedules, routes, and allocations. Evaluation of 11 language‑model configurations shows a wide performance gap, with GPT‑6.1 Sol achieving 98.7% accuracy while most models perform poorly, highlighting the challenge of constraint‑based planning in Bangla.

By Md Rayhanul Masud, S M Maksudul Alam, Mohammad Jaminur Islam

llms benchmarks

arXiv Machine Learning

Aug 5

BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems

arXiv:2608. 02612v1 Announce Type: cross Abstract: Formulating an optimization problem strongly affects the quality of the final solution, yet good formulations usually require substantial expertise.

By Yutaro Yamada, Kei Hiroshima, Nozomu Yoshinari, Kento Uchida, Shinichi Shirakawa

llms benchmarks

Related stories