Selected work

Representative Papers

Semantic Modeling for World-Centered Architectures

Apr 01, 2026

Traditional agent-centric architectures struggle to ensure semantic consistency, interpretability, and long-term stability in structured domains such as enterprises and institutional systems. This work proposes the World-centered Multi-Agent System (WMAS), a novel architectural paradigm that centers on the “world” as the primary modeling unit. By constructing a shared and explicit representation of the world, WMAS enables multi-agent learning and coordination grounded in a unified semantic model. Integrating semantic modeling, ontology engineering, and multi-agent coordination techniques, the approach structures world representations along dimensions such as ontological explicitness and normativity, thereby supporting global consistency and verifiable agent behaviors. The effectiveness of WMAS is demonstrated through the Ontobox platform, which validates its capacity to enhance semantic consistency, interpretability, and long-term system stability.

0 citationsRead paper

Don't Forget Imagination!

Aug 08, 2025

Current AI systems critically neglect cognitive imagination—the capacity to mentally construct and maintain coherent conceptual and causal systems—resulting in reasoning devoid of semantic grounding and empirical verifiability. This paper proposes, for the first time, cognitive imagination as a foundational pathway toward AI breakthroughs, introducing a novel semantic model grounded in probabilistic causal structures. The model integrates neural-network-like learning capabilities with a transparent, “glass-box” architecture to enable dynamic scenario generation, consistency maintenance, and semantic validation of imagined states. It supports context-aware inference and continuous semantic verification, achieving both strong generalization and intrinsic interpretability. The work establishes cognitive imagination as a theoretically grounded pillar of AI and delivers the first formal, model-based, and empirically verifiable framework for semantic intelligence. This advances the development of embodied, situated, and trustworthy AI systems.

0 citationsRead paper

Recent publications

Latest Papers

Semantic Modeling for World-Centered Architectures

Apr 01, 2026

Traditional agent-centric architectures struggle to ensure semantic consistency, interpretability, and long-term stability in structured domains such as enterprises and institutional systems. This work proposes the World-centered Multi-Agent System (WMAS), a novel architectural paradigm that centers on the “world” as the primary modeling unit. By constructing a shared and explicit representation of the world, WMAS enables multi-agent learning and coordination grounded in a unified semantic model. Integrating semantic modeling, ontology engineering, and multi-agent coordination techniques, the approach structures world representations along dimensions such as ontological explicitness and normativity, thereby supporting global consistency and verifiable agent behaviors. The effectiveness of WMAS is demonstrated through the Ontobox platform, which validates its capacity to enhance semantic consistency, interpretability, and long-term system stability.

0 citationsRead paper

Don't Forget Imagination!

Aug 08, 2025

Current AI systems critically neglect cognitive imagination—the capacity to mentally construct and maintain coherent conceptual and causal systems—resulting in reasoning devoid of semantic grounding and empirical verifiability. This paper proposes, for the first time, cognitive imagination as a foundational pathway toward AI breakthroughs, introducing a novel semantic model grounded in probabilistic causal structures. The model integrates neural-network-like learning capabilities with a transparent, “glass-box” architecture to enable dynamic scenario generation, consistency maintenance, and semantic validation of imagined states. It supports context-aware inference and continuous semantic verification, achieving both strong generalization and intrinsic interpretability. The work establishes cognitive imagination as a theoretically grounded pillar of AI and delivers the first formal, model-based, and empirically verifiable framework for semantic intelligence. This advances the development of embodied, situated, and trustworthy AI systems.

0 citationsRead paper