United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theory

HaoYang Shang, Xuan Liu, Zi Liang, Jie ZHANG, Haibo Hu, Song Guo

Keywords: Large Language Models, LLM Agents, Multi Agent Systems, Cognitive Load Theory, Collective Intelligence, Collaborative Reasoning, Working Memory, Complex Problem Solving, Emergent Cognition

TL;DR: LLMs hit limits on complex tasks due to cognitive overload. CoThinker, a multi-agent LLM system inspired by Cognitive Load Theory, uses specialized agents and structured communication to overcome these limits and improve problem-solving.

Abstract:

Large Language Models (LLMs) exhibit a notable performance ceiling on complex, multi-faceted tasks, as they often fail to integrate diverse information or adhere to multiple constraints.
We posit that such limitation arises when the demands of a task exceed the LLM's effective cognitive load capacity. This interpretation draws a strong analogy to Cognitive Load Theory (CLT) in cognitive science, which explains similar performance boundaries in the human mind, and is further supported by emerging evidence that reveals LLMs have bounded working memory characteristics.
Building upon this CLT-grounded understanding, we introduce ***CoThinker***, a novel LLM-based multi-agent framework designed to mitigate cognitive overload and enhance collaborative problem-solving abilities. ***CoThinker*** operationalizes CLT principles by distributing intrinsic cognitive load through agent specialization and managing transactional load via structured communication and a collective working memory. We empirically validate *CoThinker* on complex problem-solving tasks and fabricated high cognitive load scenarios, demonstrating improvements over existing multi-agent baselines in solution quality and efficiency. Our analysis reveals characteristic interaction patterns, providing insights into the emergence of collective cognition and effective load management, thus offering a principled approach to overcoming LLM performance ceilings.

Primary Area: Social and economic aspects of machine learning (e.g., fairness, interpretability, human-AI interaction, privacy, safety, strategic behavior)

Submission Number: 6610