Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systems

TL;DR

This paper introduces Trans-ACT, a novel framework embedding Transactional Analysis principles into multi-agent systems to produce agents with realistic psychological dynamics and context-aware interactions.

Contribution

It presents a new cognitive architecture integrating TA ego states into agents, enabling more human-like social behavior in multi-agent simulations.

Findings

Agents exhibit deeper, context-aware interactions in simulations.

Trans-ACT effectively models psychological dynamics of human behavior.

The framework opens new applications in conflict resolution and social psychology.

Abstract

Multi-Agent Systems (MAS) are increasingly used to simulate social interactions, but most of the frameworks miss the underlying cognitive complexity of human behavior. In this paper, we introduce Trans-ACT (Transactional Analysis Cognitive Toolkit), an approach embedding Transactional Analysis (TA) principles into MAS to generate agents with realistic psychological dynamics. Trans-ACT integrates the Parent, Adult, and Child ego states into an agent's cognitive architecture. Each ego state retrieves context-specific memories and uses them to shape response to new situations. The final answer is chosen according to the underlying life script of the agent. Our experimental simulation, which reproduces the Stupid game scenario, demonstrates that agents grounded in cognitive and TA principles produce deeper and context-aware interactions. Looking ahead, our research opens a new way for a variety of applications, including conflict resolution, educational support, and advanced social psychology studies.