04:00
2026-09-12
machinebrief.com
artificial-intelligence
When Agents Disagree: Bayesian Backward Reasoning as a Label-Free Anchor for Multi-Agent Collective Decision-Making
A new arXiv paper (2609.11709v1) proposes Bayesian backward reasoning as a label-free anchor for multi-agent collective decision-making, using Jensen-Shannon divergence to rank LLM agents by cross-pat…