Agents in the Large: Perception-Centered Architecture for Persistent Agents

• URL: http://arxiv.org/abs/2608.30478v1
• Date: Mon, 31 Aug 2026 09:04:52 GMT
• Title: Agents in the Large: Perception-Centered Architecture for Persistent Agents
• Abstract summary: We propose a Perception-Centered Architecture for Persistent Agents (Pera)<n>Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals.<n>We use Pera to retrospectively organize recent work, examine a detailed case study, and offer forward-looking insights for building more capable persistent agents.
• Score: 66.30987129595137
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence [115.91847478507736]
  LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks.<n>Many tasks require heterogeneous expertise, interdependent subtasks, parallel execution, independent verification, and persistent state.<n>We call this System Intelligence: an agent system's ability to organize and coordinate multiple intelligent components into a coherent, adaptive whole.
  arXiv  Detail & Related papers  (2026-08-21T14:27:57Z)
• A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications [18.01291032624805]
  Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex tasks.<n>Yet as agents move toward open-ended, real-world deployment, relying on from-scratch reasoning and low-level tool calls for every task become increasingly inefficient, error-prone, and hard to maintain.<n>This survey examines this challenge through the lens of emphagent skills, which we define as reusable procedural artifacts that coordinate tools, memory, and runtime context under task-specific constraints.
  arXiv  Detail & Related papers  (2026-05-08T07:10:26Z)
• AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management [24.465443389008055]
  AgentProg is a program-guided approach for agent context management.<n>It reframes the interaction history as a program with variables and control flow.<n> Experiments on AndroidWorld and our extended long-horizon task suite demonstrate that AgentProg has achieved the state-of-the-art success rates.
  arXiv  Detail & Related papers  (2025-12-11T07:37:38Z)
• An Empirical Study of Agent Developer Practices in AI Agent Frameworks [59.862193600499914]
  The rise of large language models (LLMs) has sparked a surge of interest in agents, leading to the rapid growth of agent frameworks.<n>Despite widespread use of agent frameworks, their practical applications and how they influence the agent development process remain underexplored.<n>More than 80% of developers report difficulties in identifying the frameworks that best meet their specific development requirements.
  arXiv  Detail & Related papers  (2025-12-01T17:52:15Z)
• AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications [95.42093979627703]
  AgentScope supports flexible and efficient tool-based agent-environment interactions.<n>We ground agent behaviors in the ReAct paradigm and offer advanced agent-level infrastructure.<n>AgentScope also includes robust engineering support for developer-friendly experiences.
  arXiv  Detail & Related papers  (2025-08-22T10:35:56Z)
• Agentic AI Process Observability: Discovering Behavioral Variability [2.273531916003657]
  AI agents that leverage Large Language Models (LLMs) are increasingly becoming core building blocks of modern software systems.<n> frameworks enable the definition of agent setups using natural language prompting.<n>Within such setups, agent behavior is non-deterministic for any given input.
  arXiv  Detail & Related papers  (2025-05-26T15:26:07Z)
• Asynchronous Tool Usage for Real-Time Agents [61.3041983544042]
  We introduce asynchronous AI agents capable of parallel processing and real-time tool-use. Our key contribution is an event-driven finite-state machine architecture for agent execution and prompting. This work presents both a conceptual framework and practical tools for creating AI agents capable of fluid, multitasking interactions.
  arXiv  Detail & Related papers  (2024-10-28T23:57:19Z)
• AgentScope: A Flexible yet Robust Multi-Agent Platform [66.64116117163755]
  AgentScope is a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment.
  arXiv  Detail & Related papers  (2024-02-21T04:11:28Z)
• Cognitive Architectures for Language Agents [44.89258267600489]
  We propose Cognitive Architectures for Language Agents (CoALA) CoALA describes a language agent with modular memory components, a structured action space to interact with internal memory and external environments, and a generalized decision-making process to choose actions. We use CoALA to retrospectively survey and organize a large body of recent work, and prospectively identify actionable directions towards more capable agents.
  arXiv  Detail & Related papers  (2023-09-05T17:56:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.