Agents in the Large: Perception-Centered Architecture for Persistent Agents
2026-08-31 • Computation and Language
Computation and Language
AI summaryⓘ
The authors discuss how current language-based AI agents are good at specific tasks but struggle to help continuously over a long time as needs and situations change. They propose a new framework called Pera that focuses on how these agents perceive their environment and control their actions to keep adapting and improving. This helps organize past research and guides future development toward AI that can assist persistently and handle many tasks dynamically. The work aims to shift AI design from short-term task solving to building systems that work over extended periods.
language modelscognitive agentspersistent AIperceptioncontrol systemsadaptive intelligencetask managementsoftware architectureepisodic memoryservice procedures
Authors
Shihan Dou, Haoxiang Jia, Shichun Liu, Feng Chen, Chenhao Huang, Yujiong Shen, Shaofan Liu, Jiayi Chen, Jiahang Lin, Honglin Guo, Qianyu He, Minghao Guo, Ziyi Ye, Pluto Zhou, Tao Gui, Qi Zhang, Xuanjing Huang
Abstract
Cognitive language agents have achieved substantial progress by equipping language models with memory, tools, and decision-making procedures, enabling agents to reason and act in interactive environments. Existing frameworks largely cast these agents as systems for solving user-specified, bounded tasks. An increasingly important goal is for language agents to provide persistent assistance in long-lived settings where user needs, context, and service procedures persist and change, and to remain useful across the broad range of tasks that arise over time. Yet we still lack a framework to characterize persistent AI agents, organize existing work, and guide future development. To this end, we propose a Perception-Centered Architecture for Persistent Agents (Pera). Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks. These tasks drive the ongoing operation and adaptation of the agent's service procedures. We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent agents. Just as software engineering moved from programming in the small to programming in the large, Pera frames the evolution of language agents as an analogous architectural transition toward long-lived, adaptive intelligence systems.