PaperScope
LIVE · 2026-09-15 05:40 UTC

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

Ulugbek Shernazarov, Charitha Ruwansiri Weerakon Basnayake, Abdelkhaleq El Jarjini, Noel Crespi, Praboda Rajapaksha

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.14570 v1
Category
Submitted
2026-09-13

Abstract

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: inference topology and source of inter-agent diversity. In a controlled $2 \times 3$ matrix, we cross parallel aggregation and sequential refinement with stochastic sampling, role prompting, and learned QLoRA specialization, under a fixed three-call budget and output protocol within each backbone. Using Qwen2.5-14B-Instruct and Llama-3.1-8B-Instruct, we evaluate all six configurations on multilingual low-resource emotion detection across nine languages. Parallel learned specialization is strongest on Qwen at 52.83 Macro-F1 and reaches 52.94 on Llama. On Qwen it also exceeds same-backbone zero-shot, few-shot, CoT, and seven-call self-consistency baselines. The preferred topology depends on diversity source: sequential refinement helps stochastic and prompted settings, while the learned Width advantage shrinks from 2.83 points on Qwen to 0.17 on Llama. Depth-wise analysis suggests that later learned specialists can overwrite correct early predictions, although the aggregate effect is backbone-dependent. Overall, how agents are differentiated produces larger performance shifts than topology, which should be evaluated jointly with specialization.

Comment: 23 pages, 5 figures, 25 tables. Accepted at the REALM Workshop at EMNLP 2026. Code: https://github.com/eracoding/topologyxdiversity

arXiv abs page · PDF · same-day batch