Related papers: Evolutionary Ensemble of Agents
This paper presents an evolutionary framework for the training of large language models(LLM). The models are divided into several experts(sub-networks), which have the same structure but different parameter values. Only one expert is…
While recent autonomous agents demonstrate impressive capabilities, they predominantly rely on manually scripted workflows and handcrafted heuristics, inherently limiting their potential for open-ended improvement. To address this, we…
Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to…
Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…
The rapid advancement of large language models (LLMs) has enabled the development of multi-agent systems where multiple LLM-based agents collaborate on complex tasks. However, existing systems often rely on centralized coordination, leading…
Large Language Models (LLMs) have unveiled remarkable capabilities in understanding and generating both natural language and code, but LLM reasoning is prone to hallucination and struggle with complex, novel scenarios, often getting stuck…
With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate…
Agent-based modeling and network science have been used extensively to advance our understanding of emergent collective behavior in systems that are composed of a large number of simple interacting individuals or agents. With the increasing…
Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This process places…
The presence of functional diversity within a group has been demonstrated to lead to greater robustness, higher performance and increased problem-solving ability in a broad range of studies that includes insect groups, human groups and…
Ensemble learning has gained success in machine learning with major advantages over other learning methods. Bagging is a prominent ensemble learning method that creates subgroups of data, known as bags, that are trained by individual…
In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixture of control experts (neural modules), which are gated by the latent coordinates of…
Modern deep learning systems rely on (a) a hand-tuned neural network topology, (b) massive amounts of labeled training data, and (c) extensive training over large-scale compute resources to build a system that can perform efficient image…
Evolutionary multi-objective optimization (EMO) algorithms have been demonstrated to be effective in solving multi-criteria decision-making problems. In real-world applications, analysts often employ several algorithms concurrently and…
Evolutionary optimization is a generic population-based metaheuristic that can be adapted to solve a wide variety of optimization problems and has proven very effective for combinatorial optimization problems. However, the potential of this…
Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain,…
Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…
Differential evolution (DE) is a simple but powerful evolutionary algorithm, which has been widely and successfully used in various areas. In this paper, an event-triggered impulsive control scheme (ETI) is introduced to improve the…
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.…
Large Language Model (LLM) based agents are powerful yet fundamentally static after deployment, lacking the ability to autonomously expand capabilities, generate new tools, or evolve their reasoning. This work introduces a hierarchical…