8/ This work was led by MIT PhD student Zeyuan Li (who sadly has no X) in collaboration with @lukaspet from @andonlabs and @ssnstudy.
See the paper at arxiv.org/abs/2608.14825
arxiv.org
Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce
Frontier LLM agents increasingly transact on behalf of separate principals, often using natural language rather than structured APIs. Much of the safety literature studies misaligned LLM behavior...
