Institution profile

University of Reading

Academic institutioneurope · gb
Official website
Research library23linked papers
Opportunities0open roles
Selected work

Representative Papers

Agentic AI Empowered Intent-Based Networking for 6G

Jan 10, 2026arXiv.org

This work addresses the challenge in existing intent-based networking (IBN) approaches of simultaneously achieving flexibility and interpretability in natural language understanding while strictly enforcing technical constraints—a key bottleneck for 6G autonomous orchestration. To bridge this gap, the authors propose a hierarchical multi-agent framework that integrates large language models (LLMs) with domain-expert agents. Leveraging the ReAct reasoning-action loop, the system collaboratively decomposes high-level natural language intents into network slice configurations compliant with RAN and core network constraints. This architecture represents the first approach to enable interpretable, constraint-aware, and iteratively reasoned automatic translation from intent to configuration. Experimental results demonstrate significant performance gains over rule-based systems and direct LLM prompting across diverse benchmark scenarios, validating its effectiveness in O-RAN deployments and highlighting the critical role of context-aware prompt engineering in network automation.

1 citationsRead paper
Recent publications

Latest Papers

Robustness or Crowding: Experimental Design for Trading Strategy Capacity

Aug 08, 2026

This study addresses the capacity constraints of trading strategies, wherein their profitability (or “edge”) deteriorates as capital scales up. Recognizing that existing observational metrics suffer from bias due to conflicting assumptions, the paper formulates strategy capacity for the first time as an identifiable causal inference problem. Leveraging a panel data design, it disentangles crowding effects from market impact by analyzing concurrent trades executed on the same day. Methodologically, the work integrates fixed-holding-period bias correction, variation in strategy exposure, and time-series variability analysis to demonstrate that conventional approaches systematically underestimate long-term crowding effects—and proposes a corrective framework. The study further provides practical guidelines for experimental design and a cost estimation framework, offering new tools for empirical asset pricing and quantitative investment research.

0 citationsRead paper