arXiv Machine Learning

GenOR-Twin: A Semantic Middleware for Integrating Operational Discourse with Mathematical Optimization

GenOR‑Twin is a neuro‑symbolic middleware that translates unstructured operational logs into formal constraints for mathematical optimization. It uses Large Language Models as semantic translators, not direct solvers, preserving the feasibility guarantees of exact combinatorial methods. The system dynamically injects constraints in real time, couples operational observations with a virtual model, and adapts its decision policy between schedule repair and full re‑optimization, demonstrating applicability across six optimization domains.

arXiv AI

Aug 20

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.

By Shrenil Shaun Sharma, Avi Sharma

llms

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

1d ago

TACIT: Optimization Models that Learn from Their Mistakes

arXiv:2609.38434v1 Announce Type: cross Abstract: Real-world optimization problems are difficult to model accurately because many objectives and constraints reside in domain experts' tacit knowledge,...

By Maxime Bouscary, Marco Molinaro, Sirui Li, Saurabh Amin, Ishai Menache, Konstantina Mellou

llms

arXiv AI

Jul 22

PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language

arXiv:2607. 18256v1 Announce Type: new Abstract: Optimization modeling is the process of translating real-world decision problems, often described in natural language, into formal mathematical formulations and executable solver code.

By Hongliang Lu, Zhong Li, Yuxuan Chen, Yuan Lan, Fan Zhang, Zaiwen Wen

llms benchmarks

arXiv AI

Aug 18

From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving

arXiv:2608. 14771v1 Announce Type: new Abstract: Making language models solve constraint problems reliably often means having them translate the problem into a formal specification and delegating the search to a sound solver.

By Dipankar Sarkar

llms benchmarks

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

Jul 21

NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents

arXiv:2601. 21372v3 Announce Type: replace Abstract: We present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implementations using autonomous coding agents (ACAs).

By Yang Song, Anoushka Vyas, Zirui Wei, Sina Khoshfetrat Pakazad, Henrik Ohlsson, Graham Neubig

llms agents benchmarks

arXiv Computation and Language

2d ago

SemOPT: Fixing Semantic Errors in LLM-based Optimization Modeling via Reward-Guided Search

arXiv:2609.37361v1 Announce Type: new Abstract: Operations research supports decision-making in domains such as energy, economics, and healthcare. Solving operations research problems typically begin...

By Zetong Zhou, Wentao Zhang, Jingyuan Wang, Yifan Yang, Zizhuo Wang, Shixi Hu

llms reinforcement-learning benchmarks

arXiv AI

Jun 4

The Biomimetic Architecture of Software 4.0

arXiv:2606. 04025v1 Announce Type: cross Abstract: Dominant programming paradigms inherit an execution model optimised for a bygone era of a single human mind instructing a local machine, leaving contemporary systems burdened with historical path dependencies.

By Philip Sheldrake, Dirk Scheffler

llms

arXiv AI

Jul 14

Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction

arXiv:2607. 09713v1 Announce Type: new Abstract: A key step toward autonomous industrial operation is the ability to create and reconfigure control policies from natural-language requirement specifications, with minimal or no manual redesign.

By Yuchen Wang, Javal Vyas, Tong Liu, Mehmet Mercangoz

llms agents efficiency safety

arXiv AI

Aug 11

Directed Neuro-Symbolic Stochastic Execution for Verification of Distributed Parallel AI Programs

arXiv:2608. 07947v1 Announce Type: new Abstract: Distributed parallel Artificial Intelligence (AI) programs expose reliability gaps that conventional testing cannot close: parallel executions are non-deterministic, and AI workloads bring high-dimensional inputs and non-linear operations that defeat fuzzing and symbolic execution in isolation.

By Gautham Koorma, Vikas Sharma, George Edwards, Mahdi Eslamimehr

llms benchmarks

arXiv AI

Sep 18

Large Language Models as Falsifiers for Cyber-Physical Systems

The paper introduces LLM-Falsifier, a large language model–based method for falsifying cyber‑physical system specifications written in Signal Temporal Logic (STL). By exposing the LLM to semantic cues such as natural‑language names, output trajectories, and critical‑time witnesses, the approach performs smarter, sample‑efficient robustness searches. On ARCH‑COMP benchmarks, LLM‑Falsifier outperforms existing tools across 14 of 21 specifications, requiring fewer simulations to find counterexamples.

By Ali ArjomandBigdeli, Jiawei Zhou, Stanley Bak

llms benchmarks

Related stories