Related papers: EvoGit: Decentralized Code Evolution via Git-Based…

Software development is undergoing a fundamental transformation as vibe coding becomes widespread, with large portions of contemporary codebases now being generated by Artificial Intelligence (AI). The disconnect between rapid adoption and…

This review presents a comprehensive analysis of two emerging paradigms in AI-assisted software development: vibe coding and agentic coding. While both leverage large language models (LLMs), they differ fundamentally in autonomy,…

Software debugging is a time-consuming endeavor involving a series of steps, such as fault localization and patch generation, each requiring thorough analysis and a deep understanding of the underlying logic. While large language models…

Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intelligent completion tools evolve, we need a robust evaluation…

We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and…

Complex agentic AI systems, powered by a coordinated ensemble of Large Language Models (LLMs), tool and memory modules, have demonstrated remarkable capabilities on intricate, multi-turn tasks. However, this success is shadowed by…

In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, development, these two fields have evolved distinct architectural paradigms: the…

There is a growing interest in the development of lidar-based autonomous mobility and Intelligent Transportation Systems (ITS). To operate and research on lidar data, researchers often develop code specific to application niche. This…

Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…

From the era of big science we are back to the "do it yourself", where you do not have any money to buy clusters or subscribe to grids but still have algorithms that crave many computing nodes and need them to measure scalability.…

Large Language Models (LLMs) have made significant progress in handling complex programming tasks. However, current methods rely on manual model selection and fixed workflows, which limit their ability to adapt to changing task…

This article deals with the problem of distributed machine learning, in which agents update their models based on their local datasets, and aggregate the updated models collaboratively and in a fully decentralized manner. In this paper, we…

Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and…

Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the…

This paper studies the problem of modeling multi-agent dynamical systems, where agents could interact mutually to influence their behaviors. Recent research predominantly uses geometric graphs to depict these mutual interactions, which are…

Summary: The vast generation of genetic data poses a significant challenge in efficiently uncovering valuable knowledge. Introducing GENEVIC, an AI-driven chat framework that tackles this challenge by bridging the gap between genetic data…

Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents…

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model…

Scaling vision-language models into Visual Multiagent Systems (VMAS) is hindered by two coupled issues. First, communication topologies are fixed before inference, leaving them blind to visual content and query context; second, agent…

Visual programs are executable code generated by large language models to address visual reasoning problems. They decompose complex questions into multiple reasoning steps and invoke specialized models for each step to solve the problems.…