AI RESEARCH
When Stress Becomes Signal: Detecting Antifragility-Compatible Regimes in Multi-Agent LLM Systems
arXiv CS.AI
•
ArXi:2605.02463v1 Announce Type: cross Multi-agent LLM systems are increasingly used to solve complex tasks through decomposition, debate, specialization, and ensemble reasoning. However, these systems are usually evaluated in terms of robustness: whether performance is preserved under perturbation. This paper studies a different question: whether semantic stress exposes structured variation that could future antifragile learning. We