Related papers: Advancing Automated Algorithm Design via Evolution…

In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling open scientific problems or optimizing critical pieces…

Automatic Heuristic Design (AHD) is an active research area due to its utility in solving complex search and NP-hard combinatorial optimization problems in the real world. The recent advancements in Large Language Models (LLMs) introduce…

The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this scaling capability remains severely bottlenecked by a…

Optimization algorithms are widely employed to tackle complex problems, but designing them manually is often labor-intensive and requires significant expertise. Global placement is a fundamental step in electronic design automation (EDA).…

The transition from static Large Language Models (LLMs) to self-improving agents is hindered by the lack of structured reasoning in traditional evolutionary approaches. Existing methods often struggle with premature convergence and…

Autonomous driving faces significant challenges in achieving human-like iterative decision-making, which continuously generates, evaluates, and refines trajectory proposals. Current generation-evaluation frameworks isolate trajectory…

Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but designing effective MAS architectures remains labor-intensive, brittle, and hard to generalize.…

Given the recent impressive accomplishments of language models (LMs) for code generation, we explore the use of LMs as adaptive mutation and crossover operators for an evolutionary neural architecture search (NAS) algorithm. While NAS still…

Combining large language models with evolutionary computation algorithms represents a promising research direction leveraging the remarkable generative and in-context learning capabilities of LLMs with the strengths of evolutionary…

This position paper argues that optimization problem solving can transition from expert-dependent to evolutionary agentic workflows. Traditional optimization practices rely on human specialists for problem formulation, algorithm selection,…

Recent LLM-guided evolutionary search methods have shown that iterative program mutation can discover strong algorithms, but they typically optimize each task independently, even when related tasks share reusable structure. We introduce…

Analog circuit design requires substantial human expertise and involvement, which is a significant roadblock to design productivity. Bayesian Optimization (BO), a popular machine learning based optimization strategy, has been leveraged to…

Benchmarking in continuous black-box optimisation is hindered by the limited structural diversity of existing test suites such as BBOB. We explore whether large language models embedded in an evolutionary loop can be used to design…

This paper proposes EvoAgent - an evolvable large language model (LLM) agent framework that integrates structured skill learning with a hierarchical sub-agent delegation mechanism. EvoAgent models skills as multi-file structured capability…

Optimizing scientific computing algorithms for modern GPUs is a labor-intensive and iterative process involving repeated code modification, benchmarking, and tuning across complex hardware and software stacks. Recent work has explored large…

Evolutionary multi-task optimization (EMTO) is an advanced optimization paradigm that improves search efficiency by enabling knowledge transfer across multiple tasks solved in parallel. Accordingly, a broad range of knowledge transfer…

Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better…

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…

In recent years, Large Language Models (LLMs) have demonstrated high reasoning capabilities, drawing attention for their applications as agents in various decision-making processes. One notably promising application of LLM agents is robotic…

Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathematical formulation,…