Same/opposite relational responding, a fundamental aspect of human symbolic cognition, allows the flexible generalization of stimulus relationships based on minimal experience. In this study, we demonstrate the emergence of arbitrarily applicable same/opposite relational responding within the Non-Axiomatic Reasoning System (NARS), a computational cognitive architecture designed for adaptive reasoning under uncertainty. Specifically, we extend NARS with an implementation of acquired relations, enabling the system to explicitly derive both symmetric (mutual entailment) and novel relational combinations (combinatorial entailment) from minimal explicit training in a contextually controlled matching-to-sample (MTS) procedure. Experimental results show that NARS rapidly internalizes explicitly trained relational rules and robustly demonstrates derived relational generalizations based on arbitrary contextual cues. Importantly, derived relational responding in critical test phases inherently combines both mutual and combinatorial entailments, such as deriving same-relations from multiple explicitly trained opposite-relations. Internal confidence metrics illustrate strong internalization of these relational principles, closely paralleling phenomena observed in human relational learning experiments. Our findings underscore the potential for integrating nuanced relational learning mechanisms inspired by learning psychology into artificial general intelligence frameworks, explicitly highlighting the arbitrary and context-sensitive relational capabilities modeled within NARS.

We present NARS-GPT, an integrated multi-component system, which combines the power of the Generative Pre-Trained Transformer (GPT) with the reasoning capabilities of Non-Axiomatic Reasoning System (NARS). Such combination enables the system to effectively respond to questions posed in natural language while retaining the capacity to store inferred important information for future use. The GPT element readily converts natural language into formal representations enabling seamless user interaction, while NARS performs real-time reasoning on these representations and grounds them automatically by relating them to observed events. This represents a novel solution to the symbol grounding problem which does not depend on the designer to link a selected set of pre-defined symbols to the perception model, hence allowing for autonomous acquisition of grounded concepts from natural language input at runtime. NARS-GPT is capable of long-term learning through interactive Q and A sessions with users and continuously enhances the system’s knowledge base, thereby ensuring adaptability to evolving scenarios.

This paper introduces AIRIS (Autonomous Intelligent Reinforcement Inferred Symbolism) to enable causality-based artificial intelligent agents. The system builds sets of causal rules from observations of changes in its environment which are typically caused by the actions of the agent. These rules are similar in format to rules in expert systems, however rather than being human-written, they are learned entirely by the agent itself as it keeps interacting with the environment.

We present the integration of a Non-Axiomatic Reasoning System (NARS) with mobile robots for planning and decision making. NARS enables robots to effectively handle uncertainty in real-time with complete sensor and actuator integration, thereby ensuring adaptability to evolving scenarios. We discuss essential parts of the logic, the architecture and working principles of NARS, and the integration of NARS as a ROS node. A case study is provided demonstrating the system's proficiency to carry out a garbage collection task in an open-air environment by operating a mobile robot with manipulator arm, and we demonstrate its ability to learn about the place-dependent accumulation of garbage items. Case study also reveals that our approach performs more effectively on the overall task than the Belief-Desire-Intention model we compared with.

A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as well as continuously relating sensory information to these in its perception-cognition information processing stack. The more varied the environment of a learning agent is, the more general and flexible must be these mechanisms to handle a wider variety of relevant patterns, tasks, and goal structures. While many researchers agree that information at different levels of abstraction likely differs in its makeup and structure and processing mechanisms, agreement on the particulars of such differences is not generally shared in the research community. A dual processing architecture (often referred to as System-1 and System-2) has been proposed as a model of cognitive processing, and they are often considered as responsible for low- and high-level information, respectively. We posit that cognition is not binary in this way and that knowledge at any level of abstraction involves what we refer to as neurosymbolic information, meaning that data at both high and low levels must contain both symbolic and subsymbolic information. Further, we argue that the main differentiating factor between the processing of high and low levels of data abstraction can be largely attributed to the nature of the involved attention mechanisms. We describe the key arguments behind this view and review relevant evidence from the literature.