What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
Research explores how social structure influences LLM agent behavior in multi-agent debates, revealing differences between public and off-the-record responses even without explicit objectives.
LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly to say. We study whether such social structure, without any explicit objective in the prompt, changes what an agent expresses publicly relative to an off-the-record (OTR) channel elicited under the same condition. We introduce a dual-channel debate framework in which agents produce public utterances that enter the shared history alongside OTR responses that are recorded but never shown to the other participant. Across 10 models, 3 scenarios, and
Source: What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates. Read the full piece at the source.
Summary and analysis generated by AI (mistral). Always verify against the original sources.
Measuring the Economic Effects of AI - Economic Innovation Group
