Related papers: EvoGit: Decentralized Code Evolution via Git-Based…
Software repository hosting services contain large amounts of open-source software, with GitHub hosting more than 100 million repositories, from new to established ones. Given this vast amount of projects, there is a pressing need for a…
Recent work pairs LLMs with evolutionary search to iteratively generate, modify, and select code using task-specific feedback. These systems have produced strong results in mathematical discovery and algorithm design, yet a fundamental…
Recent advances in LLM based agent systems have shown promise in tackling complex, long horizon tasks. However, existing agent protocols (e.g., A2A and MCP) under specify cross entity lifecycle and context management, version tracking, and…
Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an…
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…
LoKit is a toolkit based on the coordination language LO. It allows to build distributed collaborative applications by providing a set of generic tools. This paper briefly introduces the concept of the toolkit, presents a subset of the…
Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human…
The development of control policies for multi-robot systems traditionally follows a complex and labor-intensive process, often lacking the flexibility to adapt to dynamic tasks. This has motivated research on methods to automatically create…
Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) has emerged as a promising paradigm for enhancing LLM reasoning by retrieving multi-hop paths from KGs. However, existing KG-RAG frameworks often underperform in real-world…
Large Language Model-based multi-agent systems have shown promise in automating software development tasks. However, most vibe code systems focus on completing small tasks and incremental code changes, leaving persistent, continuous…
Automated code generation driven by Large Lan- guage Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging. Multi-agent frameworks show potential, but existing methods…
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.…
Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…
Software evolution is a fundamental process that transcends the realm of technical artifacts and permeates the entire organizational structure of a software project. By means of a longitudinal empirical study of 18 large open-source…
Foundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the…
Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve the problem. While numerous approaches have been proposed…
Generative AI technologies promise to transform the product development lifecycle. This study evaluates the efficiency gains, areas for improvement, and emerging challenges of using GitHub Copilot, an AI-powered coding assistant. We…
Generative AI is changing how software is produced and used. In vibe coding, an AI agent builds software by selecting and assembling open-source software (OSS), often without users directly reading documentation, reporting bugs, or…
Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data…
Recent advancements in generative artificial intelligence (GenAI), particularly large language models, have introduced new possibilities for software development practices. In our paper we investigate the emerging Vibe Coding (VC) paradigm…