Hierarchical Compositionality for An Assistive AI Agent

• URL: http://arxiv.org/abs/2608.10330v1
• Date: Tue, 11 Aug 2026 00:17:56 GMT
• Title: Hierarchical Compositionality for An Assistive AI Agent
• Abstract summary: AI agents are increasingly being developed to assist humans in various applications.<n>These methods are impressive predictors, but they are resource-hungry, opaque, and known to make arbitrary decisions in novel situations.<n>Our work seeks to explore the design of architectures for such AI agents based on core principles that can be traced back to the early pioneers of AI.
• Score: 9.152759278163954
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI agents are increasingly being developed to assist humans in various applications, and Large Language Models and other deep network architectures are considered to be state of the art for such agents. These methods are impressive stochastic predictors, but they are resource-hungry, opaque, and known to make arbitrary decisions in novel situations due to the narrow set of underlying representation and processing choices. Our work seeks to explore the design of architectures for such AI agents based on core principles that can be traced back to the early pioneers of AI but are not fully utilized in modern AI methods. We do so in this paper in the context of the core problem of AI agents addressing ambiguity in the objects being referred to by the human participants. Humans address such ambiguity by heuristically leveraging compositional knowledge of domain context and the preferences of the other human participants. Drawing inspiration from this observation, we describe an architecture that embeds the principle of hierarchical compositionality and uses simple heuristics to achieve the desired disambiguation. Specifically, domain objects are represented in terms of primitive attributes drawn from human-validated semantic feature norms, and a hierarchical combination of attributes and concepts automatically identified from a limited observed history of interactions of an assistive agent with specific users. The assistive agent then achieves the desired disambiguation by reasoning with knowledge of this compositional hierarchy; axioms governing domain dynamics; and models of semantic compatibility, session salience, and user-specific thematic preference, requesting human clarification when necessary. Experiments show that our approach consistently outperforms state of the art data-driven baselines, supporting adaptation to specific user profiles.

Related papers

• The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality [0.0]
  Two users with nominally equivalent AI access may experience qualitatively different AI utility.<n>For knowledge-intensive workers whose intellectual capital spans tens of thousands of files, the Context Access Divide (CAD) constitutes a qualitative threshold in AI usefulness.<n>We propose contextuality as a dimension of AI-mediated inequality that complements, but is not reducible to, the Sharp et al. framework.
  arXiv  Detail & Related papers  (2026-07-09T13:53:40Z)
• Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-agent AI [4.033017316711126]
  We propose Normative Common Ground Replication (NormCoRe) to systematically translate the design of human subject experiments into MAAI environments.<n>We show that normative judgments in AI agent studies can differ from human baselines and are sensitive to the choice of the foundation model and the language used to instantiate agent personas.
  arXiv  Detail & Related papers  (2026-03-12T14:24:29Z)
• Agentic Reasoning for Large Language Models [122.81018455095999]
  Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making.<n>Large language models (LLMs) demonstrate strong reasoning capabilities in closed-world settings, but struggle in open-ended and dynamic environments.<n>Agentic reasoning marks a paradigm shift by reframing LLMs as autonomous agents that plan, act, and learn through continual interaction.
  arXiv  Detail & Related papers  (2026-01-18T18:58:23Z)
• Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning [57.23345786304694]
  We introduce a framework for prospective learning and embedded agency centered on self-prediction.<n>We show that in multi-agent settings, self-prediction enables agents to reason about others running similar algorithms.<n>We extend the theory of AIXI, and study universally intelligent embedded agents which start from a Solomonoff prior.
  arXiv  Detail & Related papers  (2025-11-27T08:46:48Z)
• Generic-to-Specific Reasoning and Learning for Scalable Ad Hoc Teamwork [10.462598319732187]
  This paper advocates leveraging the complementary strengths of knowledge-based and data-driven methods for reasoning and learning for ad hoc teamwork.<n>For any given goal, our architecture enables each ad hoc agent to determine its actions through non-monotonic logical reasoning.<n>We experimentally evaluate our architecture's capabilities in VirtualHome, a realistic physics-based 3D simulation environment.
  arXiv  Detail & Related papers  (2025-08-06T07:44:38Z)
• AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges [3.7414278978078204]
  This review critically distinguishes between AI Agents and Agentic AI, offering a structured, conceptual taxonomy, application mapping, and analysis of opportunities and challenges to clarify their divergent design philosophies and capabilities.
  arXiv  Detail & Related papers  (2025-05-15T16:21:33Z)
• Internet of Agents: Fundamentals, Applications, and Challenges [68.9543153075464]
  We introduce the Internet of Agents (IoA) as a foundational framework that enables seamless interconnection, dynamic discovery, and collaborative orchestration among heterogeneous agents at scale.<n>We analyze the key operational enablers of IoA, including capability notification and discovery, adaptive communication protocols, dynamic task matching, consensus and conflict-resolution mechanisms, and incentive models.
  arXiv  Detail & Related papers  (2025-05-12T02:04:37Z)
• Position Paper: Agent AI Towards a Holistic Intelligence [53.35971598180146]
  We emphasize developing Agent AI -- an embodied system that integrates large foundation models into agent actions. In this paper, we propose a novel large action model to achieve embodied intelligent behavior, the Agent Foundation Model.
  arXiv  Detail & Related papers  (2024-02-28T16:09:56Z)
• An In-depth Survey of Large Language Model-based Artificial Intelligence Agents [11.774961923192478]
  We have explored the core differences and characteristics between LLM-based AI agents and traditional AI agents. We conducted an in-depth analysis of the key components of AI agents, including planning, memory, and tool use.
  arXiv  Detail & Related papers  (2023-09-23T11:25:45Z)
• Flexible and Inherently Comprehensible Knowledge Representation for Data-Efficient Learning and Trustworthy Human-Machine Teaming in Manufacturing Environments [0.0]
  Trustworthiness of artificially intelligent agents is vital for the acceptance of human-machine teaming in industrial manufacturing environments. We make use of G"ardenfors's cognitively inspired Conceptual Space framework to represent the agent's knowledge. A simple typicality model is built on top of it to determine fuzzy category membership and classify instances interpretably.
  arXiv  Detail & Related papers  (2023-05-19T11:18:23Z)
• Machine Common Sense [77.34726150561087]
  Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI) This article deals with the aspects of modeling commonsense reasoning focusing on such domain as interpersonal interactions.
  arXiv  Detail & Related papers  (2020-06-15T13:59:47Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.