The Influence of Human-inspired Agentic Sophistication in LLM-driven Strategic Reasoners

TL;DR

This paper investigates how human-inspired agentic structures influence the strategic reasoning of LLM-based agents in game scenarios, revealing that complexity and LLM capabilities critically affect human-likeness and generalisation.

Contribution

It introduces a comparative analysis of different agentic designs in LLMs and demonstrates how human-inspired structures can improve alignment with human strategic reasoning.

Findings

Human-inspired cognitive structures improve LLM agent alignment with human reasoning.

The relationship between agentic complexity and human-likeness is non-linear.

Agent generalisation is limited by underlying LLM capabilities.

Abstract

The rapid rise of large language models (LLMs) has shifted artificial intelligence (AI) research toward agentic systems, motivating the use of weaker and more flexible notions of agency. However, this shift raises key questions about the extent to which LLM-based agents replicate human strategic reasoning, particularly in game-theoretic settings. In this context, we examine the role of agentic sophistication in shaping artificial reasoners' performance by evaluating three agent designs: a simple game-theoretic model, an unstructured LLM-as-agent model, and an LLM integrated into a traditional agentic framework. Using guessing games as a testbed, we benchmarked these agents against human participants across general reasoning patterns and individual role-based objectives. Furthermore, we introduced obfuscated game scenarios to assess agents' ability to generalise beyond training distributions. Our analysis, covering over 2000 reasoning samples across 25 agent configurations, shows that human-inspired cognitive structures can enhance LLM agents' alignment with human strategic behaviour. Still, the relationship between agentic design complexity and human-likeness is non-linear, highlighting a critical dependence on underlying LLM capabilities and suggesting limits to simple architectural augmentation.