arXiv subjects

Zhao Chang

Publications and source records attributed to Zhao Chang.

3 recordsLinked to original sources

arXiv2026

The Auton Agentic AI Framework

The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users. This transition exposes a fundamental architectural mismatch: Large Language Models (LLMs) produce stochastic, unstructured outputs, whereas the backend infrastructure they must control -- databases, APIs, cloud services -- requires deterministic, schema-conformant inputs. The present paper describes the Auton Agentic AI Framework, a principled architecture for standardizing the creation, execution, and governance of autonomous agent systems. The framework is organized around a strict separation between the Cognitive Blueprint, a declarative, language-agnostic specification of agent identity and capabilities, and the Runtime Engine, the platform-specific execution substrate that instantiates and runs the agent. This separation enables cross-language portability, formal auditability, and modular tool integration via the Model Context Protocol (MCP). The paper formalizes the agent execution model as an augmented Partially Observable Markov Decision Process (POMDP) with a latent reasoning space, introduces a hierarchical memory consolidation architecture inspired by biological episodic memory systems, defines a constraint manifold formalism for safety enforcement via policy projection rather than post-hoc filtering, presents a three-level self-evolution framework spanning in-context adaptation through reinforcement learning, and describes runtime optimizations -- including parallel graph execution, speculative inference, and dynamic context pruning -- that reduce end-to-end latency for multi-step agent workflows.

cs.AI↗

arXiv2025

Overlooked weak structural connections support human cognition under nonlinear connectome scaling

Human cognition depends on large scale communication constrained by white matter architecture. Although weak connections are abundant in mammalian connectomes, they have long been treated as noise and downweighted because of tractography uncertainty in the human brain, and their relevance to human cognition and large scale functional organization remains unresolved. Across multiple datasets and tractography pipelines, we show that, when tractography derived connectivity weights are interpreted through a nonlinear weighting framework, weak connections make measurable contributions to cognitive prediction, functional connectivity simulation, and structure-function coupling. These effects are selective: nonlinear weighting improves the prediction of general cognitive ability and memory more than that of crystallized intelligence or processing speed, consistent with the notion that weak connections preferentially expand the modal repertoire of brain networks to enhance both large scale integration and fine grained segregation, thereby supporting the functional balance essential for diverse cognitive abilities. Importantly, these effects are replicated in a reliability aware connectome generated by integrating two post tractography filtering methods, in which preserving weak links consistently outperforms conventional thresholding strategies. Finally, we show that weak connections contain functionally informative subsets organized along systems level and transcriptomic gradients. In particular, a specific class of weak connections, predominantly linking visual and motor systems with limbic regions and characterized by negative gene coexpression, exerts a disproportionately large influence on brain function.

q-bio.NC↗

arXiv2025

Beyond variance: sensitivity-based dimensions in brain networks underlie individual differences in cognitive ability

Explaining individual differences in cognitive abilities requires both identifying brain parameters that vary across individuals and understanding how brain networks are recruited for specific tasks. Typically, task performance relies on the integration and segregation of functional subnetworks, often captured by parameters like regional excitability and connectivity. Yet, the high dimensionality of these parameters hinders pinpointing their functional relevance. Here, we apply stiff-sloppy analysis to human brain data, revealing that certain subtle parameter combinations ("stiff dimensions") powerfully influence neural activity during task processing, whereas others ("sloppy dimensions") vary more extensively but exert minimal impact. Using a pairwise maximum entropy model of task fMRI, we show that even small deviations in stiff dimensions-derived through Fisher Information Matrix analysis-govern the dynamic interplay of segregation and integration between the default mode network (DMN) and a working memory network (WMN). Crucially, separating a 0-back task (vigilant attention) from a 2-back task (working memory updating) uncovers partially distinct stiff dimensions predicting performance in each condition, along with a global DMN-WMN segregation shared across both tasks. Altogether, stiff-sloppy analysis challenges the conventional focus on large parameter variability by highlighting these subtle yet functionally decisive parameter combinations.

q-bio.NC↗