RESEARCH

Beyond Symmetric Agents: Cognitive Diversity and Multi-Agent Debate in Small Language Models

ArXiv cs.AI · Wed, 30 Sep 2026 04:00:00 GMT

arXiv:2609.35875v1 Announce Type: new Abstract: Multi-agent debate (MAD) reportedly improves reasoning and factuality over single-model inference, but prior work treats agents as symmetric peers, leaving open what drives the gains. We test the hypothesis that cognitive diversity

Read original source Discuss with SiiMON