arXiv AI

Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero

The paper introduces a dual‑agent framework that automates the evolution of Meta‑Black‑Box Optimization (MetaBBO) algorithms. By treating the design loop as a coding task, a task agent refines the MetaBBO codebase while a hyper agent continually modifies both agents, enabling recursive self‑improvement. The resulting evolved MetaBBO variants outperform current human‑crafted baselines and adapt quickly across different optimization domains, revealing emergent design principles.

arXiv AI

Oct 1

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 AI

Jul 7

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

arXiv:2607. 03451v1 Announce Type: cross Abstract: While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines.

By Yifei Shen, Bo Li, Xinjie Zhang

llms agents

arXiv AI

5d ago

A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization

The paper introduces AgenticBBO-Bench, a cross‑domain benchmark for evaluating large language model agents on black‑box optimization tasks such as synthetic functions, hyperparameter tuning, database tuning, chip design, and molecular design. Experiments show that agentic BBO outperforms direct LLM‑based methods in all five domains and beats the best numerical optimizers in four. The study also analyzes the impact of optimization tools, task semantics, prior knowledge, and the LLM’s role, finding that numerical tools are not consistently helpful, task semantics are broadly useful, and numerical optimizers can capitalize on agent‑generated search trajectories.

By Ming Chen, Rong-Xi Tan, Ke Xue, Yu-Jie Zhou, Taiye Lu, Zhi-Xuan Gao, Peng Xie, Zijun Shen, Chen Lu, Haopu Shang, Chao Qian

llms agents benchmarks

arXiv AI

Oct 1

Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization

arXiv:2609.38757v1 Announce Type: new Abstract: Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorit...

By Chen Lu, Ke Xue, Siyuan Xu, Mingxuan Yuan, Chao Qian

llms agents efficiency benchmarks

arXiv AI

Jun 3

Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization

arXiv:2604. 17708v2 Announce Type: replace Abstract: Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows.

By Jiahao Huang, Peilan Xu, Xiaoya Nan, Wenjian Luo

llms agents benchmarks safety

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 30

SimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priors

arXiv:2609.37172v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuri...

By Jianghan Zhu, Cong Zhang, Rongjie Zhu, Chi Zhang, Zhiguang Cao

llms agents

arXiv Machine Learning

Sep 30

HeurEvo: Agentic Evolution of Hybrid Solver-Augmented Heuristics for Time-Critical Mathematical Optimization

arXiv:2609.36303v1 Announce Type: cross Abstract: Recent advances in agentic heuristic design use AI agents and execution feedback to automate algorithm discovery for challenging optimization problem...

By Feijie Wu, Hugo Barbalho, Konstantina Mellou, Marco Molinaro, Jing Gao, Ishai Menache, Xinzhi Zhang, Sirui Li

agents benchmarks

arXiv Machine Learning

Jun 25

ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments

arXiv:2606. 25207v1 Announce Type: new Abstract: Hyperparameter Optimization (HPO) is essential for maximizing machine learning model performance, and its core challenge is sample efficiency: finding strong configurations within a limited budget.

By Taicheng Guo, Haomin Zhuang, Kehan Guo, Yujun Zhou, Nitesh V. Chawla, Olaf Wiest, Xiangliang Zhang

llms agents safety

arXiv AI

Jul 24

OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining

arXiv:2607. 20486v1 Announce Type: new Abstract: Designing optimizers for modern deep learning remains a challenging scientific problem, requiring the joint consideration of optimization geometry, state dynamics, numerical stability, implementation constraints, and empirical generalization.

By Zhongzheng Li, Tiancan Feng, Wenhao Li, Qingsong Ran, Shikun Feng, Xiaoyuan Zhang, Yue Wang, Xiaoguang Zhao

llms agents

arXiv AI

Sep 4

Evolving Excellence: Automated Optimization of LLM-based Agents

The paper introduces ARTEMIS, a no-code evolutionary optimization platform that automatically tunes large language model (LLM) agents by jointly optimizing prompts, tool descriptions, and parameters using semantically-aware genetic operators. Starting from a benchmark script and natural language goals, ARTEMIS discovers configurable components, extracts performance signals from execution logs, and evolves configurations without architectural changes. Experiments on four agent systems show significant gains: a 13.6% increase in acceptance rate for the ALE Agent, a 10.1% performance boost for the Mini‑SWE Agent, a 36.9% token‑reduction for the CrewAI Agent, and a 22% accuracy improvement for the MathTales‑Teacher Agent using a smaller open‑source model.

By Paul Brookes, Vardan Voskanyan, Rafail Giavrimis, Matthew Truscott, Mina Ilieva, Chrystalla Pavlou, Alexandru Staicu, Manal Adham, Will Evers- Hood, Jingzhi Gong, Kejia Zhang, Matvey Fedoseev, Vishal Sharma, Roman Bauer, Zheng Wang, Hema Nair, Wei Jie, Tianhua Xu, Aurora Constantin, Leslie Kanthan, Michail Basios

llms agents benchmarks

arXiv AI

Sep 2

AgentFactory: Towards Automated Agentic System Design and Optimization

arXiv:2609.01045v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and...

By Enci Zhang, Haofeng Wang, Yuesheng Zhu, Xiaole Cui, Guibo Luo

llms agents fine-tuning benchmarks

Related stories