works on
agent safety 1large language models 1multi-agent systems 1resource allocation 1runtime constraints 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.AI2026

Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory

Tengjiao Liu

The paper proposes a heterogeneous cohort of LLM agents—Disrupter, Validator, and Broker—that separate creativity from safety, using runtime-checked constraint patches called Scars…