Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Emotion Detection

Ulugbek Shernazarov, Charitha Ruwansiri Weerakon Basnayake, Abdelkhaleq El Jarjini +2

Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We study these factors independently…