The field of autonomous systems and AI is rapidly advancing, with a focus on developing innovative solutions that integrate AI-driven technologies. Recent developments have centered around creating autonomous agents that can interact with each other and their environment, enabling more efficient and adaptive systems.

One of the key directions in this field is the development of multi-agent systems that can perceive their environment, make decisions, and take actions autonomously. These systems have the potential to revolutionize various areas, including networking, software engineering, and decision-making.

Noteworthy papers in this area include:

• Design and Evaluation of a Multi-Agent Perception System for Autonomous Flying Networks, which presents a modular and scalable system for autonomous perception in flying networks.
• Towards autonomous normative multi-agent systems for Human-AI software engineering teams, which introduces a new class of software engineering agents empowered by Large Language Models.
• Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions, which proposes a conceptual transition from model-level safety to system-level safety in interacting LLMs.