Recursively Self-Improving Electromagnetic Spectrum Agents: Architecture and Operation
Organizations: The authors are with Nanjing University of Aeronautics and Astronautics.
Abstract
Electromagnetic spectrum agents (ESAs) must contend with changing environments and task requirements during sustained autonomous operation, yet their existing capabilities may not remain suitable for new operating conditions. This article proposes recursively self-improving electromagnetic spectrum agents (RSI-ESAs) that use operational feedback to update their capabilities and build on prior improvements. We present their architecture and editable components, and describe a self-improvement process encompassing problem diagnosis, candidate generation, validation, and inheritance. By retaining effective task versions and using modification records and diagnostic knowledge to guide subsequent updates, RSI-ESAs can accumulate task capabilities and improvement experience across successive rounds. A shared-spectrum scheduling case study illustrates improved task performance and capability accumulation over multiple improvement rounds under the tested conditions. Finally, we discuss open challenges for broader tasks and long-term operation, outlining research directions for the continued capability development of ESAs.
Figures & tables
| Editable object | Role |
| State processing | Improve the state representation used for decisions |
| Resource decisions | Change how limited resources are allocated across tasks |
| Feedback handling | Use execution feedback to organize subsequent actions |
| Tool organization | Compose or extend executable task procedures |
| Improvement experience | Inform subsequent diagnosis and candidate generation |
Self-Improving Agents
Self-improving agents use experience and feedback to update their models, memories, skills, or workflows for better future task performance.
See all 198 papers