Cheap Talk, Empty Promise: Frontier LLMs easily break public promises for self-interest

Jerick Shi, Terry Jingchen Zhang, Vincent Conitzer, Zhijing Jin

Keywords: LLM, Incentive-driven deception, public commitments, cheap talk, commitment breaking, normal-form games;

TL;DR: LLM agents break public promises in ~57% of game-theoretic scenarios, primarily through unreflective payoff optimization rather than deliberate deception, with the character of lying varying substantially across models and games.

Abstract: Large language models are increasingly deployed as autonomous agents in multi-agent settings where they communicate intentions and take consequential actions with limited human oversight. A critical safety question is whether agents that publicly commit to actions break those promises when they can privately deviate, and what the consequences are for both themselves and the collective. We study deception as a deviation from a publicly announced action in one-shot normal-form games, classifying each deviation by its effect on individual payoff and collective welfare into four categories: strategic, selfish, altruistic, and sabotaging. By exhaustively enumerating announcement profiles across six canonical games and nine frontier models, we identify all opportunities for each deviation type and measure how often agents exploit them. Across all settings, agents deviate from promises in approximately 56.6\% of scenarios, but the character of deception varies substantially across models even at similar overall rates. Most critically, for the majority of the models, promise-breaking occurs without metacognitive awareness as measured by LLM-judged reasoning traces, with agents optimizing payoffs without recognizing that they are breaking promises.

Track: Long Paper

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 98