Related papers: From Seed AI to Technological Singularity via Recu…
Recursive self-improving (RSI) systems have been dreamed of since the early days of computer science and artificial intelligence. However, many existing studies on RSI systems remain philosophical, and lacks clear formulation and results.…
Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as…
We have designed a machine that becomes increasingly better at behaving in underspecified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as experience accumulates. Based on principles of…
The scarcity of high-quality training data presents a fundamental bottleneck to scaling machine learning models. This challenge is particularly acute in recommendation systems, where extreme sparsity in user interactions leads to rugged…
Many problems related to the quality of requirements arise during elicitation and specification activities since they are written in natural language. The flexibility and inherent nature of language make requirements prone to…
AI systems improve by drawing on more compute, data, energy, and better training methods. This paper asks a precise, testable version of the "runaway growth" question: under what measurable conditions could capability escalate without bound…
Recursive Self-Improvement (RSI) enables intelligence systems to autonomously refine their capabilities. This paper explores the application of RSI in text-to-image diffusion models, addressing the challenge of training collapse caused by…
As modern software systems grow in complexity and scale, their ability to autonomously detect, diagnose, and recover from failures becomes increasingly vital. Drawing inspiration from biological healing - where the human body detects…
Software automation has long been a central goal of software engineering, striving for software development that proceeds without human intervention. Recent efforts have leveraged Artificial Intelligence (AI) to advance software automation…
Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…
Context: The rise of Artificial Intelligence (AI) in software engineering has led to the development of AI-powered test automation tools, promising improved efficiency, reduced maintenance effort, and enhanced defect-detection. However, a…
Testing and code reviews are known techniques to improve the quality and robustness of software. Unfortunately, the complexity of modern software systems makes it impossible to anticipate all possible problems that can occur at runtime,…
Software systems impact society at different levels as they pervasively solve real-world problems. Modern software systems are often so sophisticated that their complexity exceeds the limits of human comprehension. These systems must…
The singularity refers to an idea that once a machine having an artificial intelligence surpassing the human intelligence capacity is created, it will trigger explosive technological and intelligence growth. I propose to test the hypothesis…
We study the problem of automated hypersafety verification of infinite-state recursive programs. We propose an infinite class of product programs, specifically designed with recursion in mind, that reduce the hypersafety verification of a…
Reproducibility is one of the core dimensions that concur to deliver Trustworthy Artificial Intelligence. Broadly speaking, reproducibility can be defined as the possibility to reproduce the same or a similar experiment or method, thereby…
With the increasing complexity of software systems, it becomes very difficult to install, configure, adjust, and maintain them. As systems become more interconnected and diverse, system architects are less able to predict and design the…
The openness of modern IT systems and their permanent change make it challenging to keep these systems secure. A combination of regression and security testing called security regression testing, which ensures that changes made to a system…
We present Noise-to-Meaning Recursive Self-Improvement (N2M-RSI), a minimal formal model showing that once an AI agent feeds its own outputs back as inputs and crosses an explicit information-integration threshold, its internal complexity…
Sequential learning systems are used in a wide variety of problems from decision making to optimization, where they provide a 'belief' (opinion) to nature, and then update this belief based on the feedback (result) to minimize (or maximize)…