Related papers: Better AI through Logical Scaffolding
Many conversational user interfaces facilitate linear conversations with turn-based dialogue, similar to face-to-face conversations between people. However, digital conversations can afford more than simple back-and-forth; they can be…
Robotic Process Automation (RPA) systems face challenges in handling complex processes and diverse screen layouts that require advanced human-like decision-making capabilities. These systems typically rely on pixel-level encoding through…
Current approaches to making programming languages and reasoning assistants more effective for people focus on leveraging feedback from users and on evaluating the success of particular techniques. These approaches, although helpful, may…
Research exploring how to support decision-making has often used machine learning to automate or assist human decisions. We take an alternative approach for improving decision-making, using machine learning to help stakeholders surface ways…
While neural networks are good at learning unspecified functions from training samples, they cannot be directly implemented in hardware and are often not interpretable or formally verifiable. On the other hand, logic circuits are…
Large Language Models (LLMs) have rapidly transformed the landscape of artificial intelligence, enabling natural language interfaces and dynamic orchestration of software components. However, their reliance on probabilistic inference limits…
Causal discovery through experimentation and intervention is fundamental to robust problem solving. It requires not just updating beliefs within a fixed framework but revising the hypothesis space itself, a capacity current AI agents lack…
Planning is a pivotal ability of any intelligent system being developed for real-world applications. AI planning is concerned with researching and developing planning systems that automatically compute plans that satisfy some user…
While the increased integration of AI technologies into interactive systems enables them to solve an equally increasing number of tasks, the black box problem of AI models continues to spread throughout the interactive system as a whole.…
The recent rapid advancement of LLM-based AI systems has accelerated our search and production of information. While the advantages brought by these systems seemingly improve the performance or efficiency of human activities, they do not…
Modelling the logical architecture of an automotive system as one central step in the development process leads to an early understanding of the fundamental functional properties of the system under design. This supports developers in…
One goal of AI (and AGI) is to identify and understand specific mechanisms and representations sufficient for general intelligence. Often, this work manifests in research focused on architectures and many cognitive architectures have been…
In this report, a novel approach to intelligence and learning is introduced, this approach is based on what we call 'perception logic'. Based on this logic, a computing mechanism and automata are introduced. Multi-resolution analysis of…
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video…
OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…
Logic can be made useful for programming and for databases independently of logic programming. To be useful in this way, logic has to provide a mechanism for the definition of new functions and new relations on the basis of those given in…
The human reasoning process is seldom a one-way process from an input leading to an output. Instead, it often involves a systematic deduction by ruling out other possible outcomes as a self-checking mechanism. In this paper, we describe the…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
We need to look at our shoelaces as we first learn to tie them but having mastered this skill, can do it from touch alone. We call this phenomenon "sensory scaffolding": observation streams that are not needed by a master might yet aid a…
Software testing remains critical for ensuring reliability, yet traditional approaches are slow, costly, and prone to gaps in coverage. This paper presents an AI-driven framework that automates test case generation and validation using…