Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems

TL;DR

This paper presents a heartbeat-driven scheduling mechanism for LLM agents that enables proactive, adaptive self-regulation of cognitive modules, inspired by human cognition rhythms, improving flexibility and efficiency.

Contribution

It introduces a novel heartbeat-based scheduler with a meta-learning strategy for dynamic, continual adaptation of cognitive modules in LLM systems.

Findings

The approach learns to schedule cognitive activities based on historical data.

It allows dynamic addition or removal of cognitive modules without reengineering.

The system effectively integrates new thinking modules autonomously.

Abstract

Large Language Model (LLM) agents have demonstrated remarkable capabilities in reasoning and tool use, yet they often suffer from rigid, reactive control flows that limit their adaptability and efficiency. Most existing frameworks rely on fixed pipelines or failure-triggered reflection, causing agents to act impulsively or correct errors only after they occur. In this paper, we introduce Heartbeat-Driven Autonomous Thinking Activity Scheduling, a mechanism that enables proactive, adaptive, and continuous self-regulation. Mirroring the natural rhythm of human cognition, our system employs a periodic ``heartbeat'' mechanism to orchestrate a dynamic repertoire of cognitive modules (e.g., Planner, Critic, Recaller, Dreamer). Unlike traditional approaches that rely on hard-coded symbolic rules or immediate reactive triggers, our scheduler learns to determine when to engage specific thinking activities -- such as recalling memories, summarizing experiences, or strategic planning -- based on temporal patterns and historical context. This functional approach allows cognitive modules to be dynamically added or removed without structural reengineering. Meanwhile, we propose a meta-learning strategy for continual policy adaptation, where the scheduler optimizes its cognitive strategy over time using historical interaction logs. Evaluation results demonstrate that our approach effectively learns to schedule cognitive activities based on historical data and can autonomously integrate new thinking modules.