arXiv Machine Learning August 11, 2026 By V\'ictor Gallego

A Hybrid Nested Harness for Decoupling Structure and Parameters in LLM-Driven Optimization

Read the original on arXiv Machine Learning →

arXiv:2608. 08156v1 Announce Type: new Abstract: In evolutionary algorithms powered by language models, the LLM acts as a single operator that simultaneously updates structural components (like control flow) and continuous parameters.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv Machine Learning

Aug 6

GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs

arXiv:2606. 23299v2 Announce Type: replace Abstract: Configuring the hyperparameters of Mixed-integer programming (MIP) solvers is a high-dimensional, instance-dependent optimization problem where suboptimal settings can degrade solving time by orders of magnitude.

By Yidong Luo, Xuemin Chen, Chenguang Wang, Fangzhou Zhu, Tao Zhong, Tianshu Yu

llms benchmarks

arXiv AI

Jul 7

A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving

arXiv:2509. 08269v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly integrated with evolutionary computation to support optimization tasks.

By Yisong Zhang, Ran Cheng, Guoxing Yi, Kay Chen Tan

llms agents benchmarks

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 Machine Learning

Aug 4

Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch

arXiv:2608. 00316v1 Announce Type: new Abstract: Bayesian optimization (BO) has become the standard tool for sample-efficient optimization and owes its efficiency to uncertainty-aware search driven by generic statistical priors.

By Paul Brunzema, Louis Tiao, Nhat Le, Kevin De Angeli, Yao Xuan, Djordje Gligorijevic

llms agents benchmarks

arXiv Machine Learning

Jun 9

Large-scale empirical tuning and comparison of default optimizers for variational inference

arXiv:2606. 07841v1 Announce Type: cross Abstract: Black-box variational inference (BBVI) is a methodology for posterior approximation that relies on stochastic optimization.

By Trevor Campbell, Jonathan H. Huggins, Kyurae Kim, Charles C. Margossian

benchmarks

arXiv Machine Learning

Sep 4

Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings

Frontier large language models (LLMs) are examined as batch optimizers in both continuous and discrete settings. The study finds that while LLMs perform competitively in zero‑shot optimization of numerical test functions, their performance is less robust than classical non‑LLM methods. However, LLMs excel in semantically rich, discrete spaces that resemble their pretraining data, demonstrating strong batch optimization behavior in such contexts.

By Frank Hu, Shriram Chennakesavalu, David Graff

llms

One email a morning, machine-written

Related stories

GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs

A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving

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

Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch

Large-scale empirical tuning and comparison of default optimizers for variational inference

Frontier LLMs are effective batch optimizers: Assessing reasoning models in continuous and discrete settings