arXiv AI August 11, 2026 By Ruibo Duan, Yuxin Liu, Haoran Ye, Xinyao Dong, Zhiqiang Xu, Chenglin Fan

ACEvo: Adversarial Co-Evolution of Problem Distributions and Solvers for Combinatorial Optimization

arXiv:2506. 02594v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to synthesize heuristic programs, yet most existing pipelines optimize solvers against fixed benchmark distributions.

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 AI.

arXiv AI

Sep 10

An Evolutionary Framework for Automatic Optimization Benchmark Generation via Large Language Models

The paper introduces LLM-EBG, an evolutionary framework that uses a large language model as a generative operator to automatically create optimization benchmarks. By generating unconstrained single-objective continuous minimization problems expressed as mathematical formulas, the framework can produce benchmarks that consistently favor a target algorithm over a comparison algorithm in over 80% of trials. Landscape analysis shows that these generated problems exhibit distinct geometric traits, such as sensitivity to variable scaling, reflecting the search behaviors of different optimization methods.

By Yuhiro Ono, Tomohiro Harada, Yukiya Miura

llms benchmarks

arXiv AI

Jun 26

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

arXiv:2606. 26578v1 Announce Type: new Abstract: Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges.

By Qingcan Kang, Mingyang Liu, Xiaojin Fu, Shixiong Kai, Tao Zhong, Mingxuan Yuan

llms agents reinforcement-learning fine-tuning

arXiv AI

Aug 11

MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design

arXiv:2608. 07544v1 Announce Type: cross Abstract: Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs).

By Oguzhan Gungordu, Siheng Xiong, Faramarz Fekri

llms benchmarks safety

arXiv AI

2d ago

Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer

The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.

By Qiankai Xu

agents benchmarks

arXiv Machine Learning

Jul 27

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

arXiv:2607. 21971v1 Announce Type: new Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.

By Shujin Wu, Cheng Qian, Xiusi Chen, Heng Ji

llms reinforcement-learning benchmarks

arXiv AI

Sep 10

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation

arXiv:2604.16625v2 Announce Type: replace-cross Abstract: Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improv...

By Weihua Du, Jingming Zhuo, Yixin Dong, Andre Wang He, Weiwei Sun, Zeyu Zheng, Manupa Karunaratne, Ivan Fox, Tim Dettmers, Tianqi Chen, Yiming Yang, Sean Welleck

llms agents fine-tuning benchmarks

One email a morning, machine-written

Related stories

An Evolutionary Framework for Automatic Optimization Benchmark Generation via Large Language Models

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design

Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation