Sepehr Ilami
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Steering Emergent Behavior in Multi-Agent LLM Systems via Information Networks
According to the abstract, Sepehr Ilami and Babak Heydari study how deciding which language model agent observes which other agent affects group outcomes. Ten identical agents played repeated group-decision games across 1,080 episodes; the abstract says the value of information depends on whether individually attractive behavior matches the collective goal.