Related papers: Autopoiesis: A Self-Evolving System Paradigm for L…

Autonomous agents can adapt their behaviour to changing environments, but remain bound to requirements, goals, and capabilities fixed at design time, preventing genuine software evolution. This paper introduces self-evolving software…

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 driving technology, a catalyst for revolutionizing transportation and urban mobility, has the tend to transition from rule-based systems to data-driven strategies. Traditional module-based systems are constrained by cumulative…

With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…

Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software development to customer support. However, LLM agents often underperform due to suboptimal configurations;…

Multi-objective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional evolutionary algorithms (EAs), though effective, often rely on…

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and…

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments…

Self-adaptive systems increasingly operate in close interaction with humans, often sharing the same physical or virtual environments and making decisions with ethical implications at runtime. Current approaches typically encode ethics as…

Efficiently serving large language models (LLMs) under dynamic and bursty workloads remains a key challenge for real-world deployment. Existing serving frameworks and static model compression techniques fail to adapt to workload…

Large Language Model (LLM) agents have demonstrated remarkable capabilities in reasoning and tool use, yet they often suffer from rigid, reactive control flows that limit their adaptability and efficiency. Most existing frameworks rely on…

In the quest for super-human performance, Large Language Models (LLMs) have traditionally been tethered to human-annotated datasets and predefined training objectives-a process that is both labor-intensive and inherently limited. This paper…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

The rise of large language models (LLMs) has created new opportunities across various fields but has also introduced significant challenges in resource management. Current LLM serving systems face a fundamental tension: balancing serving…

Large Language Models (LLMs) have enabled the emergence of LLM agents, systems capable of pursuing under-specified goals and adapting after deployment. Evaluating such agents is challenging because their behavior is open ended,…

Large Language Models (LLMs) can be fine-tuned on domain-specific data to enhance their performance in specialized fields. However, such data often contains numerous low-quality samples, necessitating effective data processing (DP). In…

Online ride-hailing platforms aim to deliver efficient mobility-on-demand services, often facing challenges in balancing dynamic and spatially heterogeneous supply and demand. Existing methods typically fall into two categories:…

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

We demonstrate the ability of large language models (LLMs) to perform iterative self-improvement of robot policies. An important insight of this paper is that LLMs have a built-in ability to perform (stochastic) numerical optimization and…

Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new type of workload, agentic pipeline search, in which autonomous or semi-autonomous agents generate,…