Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models

Younwoo Choi, Changling Li, Yongjin Yang, Zhijing Jin

Keywords: LLM/AI agents, safety and alignment, security and privacy

TL;DR: This paper formalizes and evaluates interlocutor awareness—LLMs’ ability to detect and adapt to a partner’s identity—showing its benefits for collaboration and its risks for safety (e.g., jailbreaks).

Abstract: As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable performance and robust safety. While prior work has extensively studied situational awareness—an LLM’s ability to recognize its operating phase and constraints—it has largely overlooked the complementary capacity to identify and adapt to the identity and characteristics of a dialogue partner. In this paper, we formalize this latter capability as interlocutor awareness and present the first systematic evaluation of its emergence in contemporary LLMs. We examine interlocutor inference across three dimensions—reasoning patterns, linguistic style, and alignment preferences—and show that LLMs reliably identify same-family peers and certain prominent model families, such as GPT and Claude. To demonstrate its practical significance, we develop three case studies in which interlocutor awareness both enhances multi-LLM collaboration through dynamic prompt adaptation and introduces new alignment and safety vulnerabilities, including reward-hacking behaviors and increased jailbreak susceptibility. Our findings highlight the dual promise and peril of identity-sensitive behavior in LLMs, underscoring the need for further understanding of interlocutor awareness and new safeguards in multi-agent deployments.

Submission Number: 9