The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
Xinrun Wang, Chang Yang, He Zhao, Zhuoyi Lin, Shuyue Hu

TL;DR
This paper proposes a new theoretical framework called Agent Cybernetics, based on cybernetics principles, to improve the design, reliability, and safety of large language model-based foundation agents in complex tasks.
Contribution
It introduces the concept of Agent Cybernetics, mapping classical cybernetics laws to agent design principles, providing a scientific foundation for reliable, self-improving foundation agents.
Findings
Identifies failure modes in agent applications like code generation and research
Provides concrete engineering recommendations for agent reliability and safety
Synthesizes cybernetics principles into design desiderata for agents
Abstract
LLM-based foundation agents that perceive, reason, and act across thousands of reasoning steps are rapidly becoming the dominant paradigm for deploying artificial intelligence in open-ended, long-horizon complex tasks. Despite this significance, the field remains overwhelmingly engineering-driven. Engineering practice has converged on useful primitives (tool loops, memory banks, harnesses, reflection steps), yet these are assembled by empirical trial and error rather than from first principles. Fundamental questions remain open: under what conditions does a long-running agent remain on-task? How should an agent respond when its environment exceeds its representational capacity? What architectural properties are necessary for safe self-improvement? We argue that cybernetics, the mid-twentieth-century science of control and communication in complex systems, provides the missing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
