Related papers: Escher-Loop: Mutual Evolution by Closed-Loop Self-…
Autonomous agents are increasingly used to improve prompts, code, and machine learning systems through iterative execution and feedback. Yet existing approaches are usually designed as task-specific optimization loops rather than as a…
Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and…
The fusion of the multi-agent paradigm with evolutionary computation yielded promising results in many optimization problems. Evolutionary multi-agent system (EMAS) are more similar to biological evolution than classical evolutionary…
Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement.…
Evolutionary strategies have recently been shown to achieve competing levels of performance for complex optimization problems in reinforcement learning. In such problems, one often needs to optimize an objective function subject to a set of…
Designing protocols enhancing cooperation for multi-agent systems remains a grand challenge. Cheap talk, defined as costless, non-binding communication before formal action, serves as a pivotal solution. However, existing theoretical…
Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance on static toolsets or offline training lags behind these dynamics, leaving…
Evolutionary processes proved very useful for solving optimization problems. In this work, we build a formalization of the notion of cooperation and competition of multiple systems working toward a common optimization goal of the population…
We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as…
We integrate dual-process theories of human cognition with evolutionary game theory to study the evolution of automatic and controlled decision-making processes. We introduce a model where agents who make decisions using either automatic or…
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…
Autonomous vehicles in interactive traffic environments are often limited by the scarcity of safety-critical tail events in static datasets, which biases learned policies toward average-case behaviors and reduces robustness. Existing…
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…
The fast-slow dynamics of an eco-evolutionary system are studied, where we consider the feedback actions of environmental resources that are classified into those that are self-renewing and those externally supplied. We show although these…
Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps,…
Automating the end-to-end scientific research process poses a fundamental challenge: it requires both evolving high-level plans that are novel and sound, and executing these plans correctly amidst dynamic and uncertain conditions. To…
The evolution of specialization in a multi-agent system is studied both by computer simulation and Markov process model. Many individual agents search for and exploit resources to get global optimization in an environment without complete…
This paper presents an evolutionary algorithm with a new goal-sequence domination scheme for better decision support in multi-objective optimization. The approach allows the inclusion of advanced hard/soft priority and constraint…
Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more critically, designing sophisticated optimizers, architectures,…
On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…