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

Hugging Face Daily Papers Papers

Summary

The paper proposes a Perception-Centered Architecture (Pera) for persistent language agents that continuously adapt service procedures by perceiving signals from tasks, context, and environmental changes. It organizes existing work and provides insights for building more capable persistent agents.

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.
Original Article
View Cached Full Text

Cached at: 09/02/26, 07:44 AM

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

Source: https://huggingface.co/papers/2608.30478 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

The paper proposes a perception-centered architecture for persistent language agents that continuously adapt service procedures by perceiving signals from tasks, context, and environmental changes.

Cognitive language agents have achieved substantial progress by equippinglanguage modelswith 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 aPerception-Centered ArchitectureforPersistent 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 constructlifecycle 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 capablepersistent 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.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2608\.30478

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.30478 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.30478 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.30478 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Persistent Semantic Entities in Tool-Augmented LLM Systems

arXiv cs.LG

This paper formalizes Persistent Semantic Entities (PSE) in tool-augmented LLM agents, showing that implicit state persists across sessions and can be exploited, with all tested models vulnerable to preference and instruction contamination.