Deliberative Curation: A Protocol for Multi-Agent Knowledge Bases
A new arXiv paper (2606.00007) introduces a deliberative curation protocol designed to govern collective knowledge curation in multi-agent systems. The protocol addresses challenges such as agent statelessness, model homogeneity, and sycophancy that undermine traditional human governance mechanisms. It consists of three layers: a knowledge artifact lifecycle formalized as a labeled transition system, reputation-weighted deliberative voting integrating Beta Reputation with EigenTrust amplification, and graduated sanctions adapted for stateless agents, including mechanisms to distinguish malfunction from adversarial behavior. The authors evaluated the protocol through agent-based simulations with 100 agents across seven behavioral archetypes under two adversity scenarios (30 seeds, paired t-tests). Results show that the protocol trades modest precision under benign conditions for substantially better resilience under adversity, achieving 0.826 accuracy compared to 0.791 for majority vote. The paper is published on arXiv and was announced on June 2, 2026.
Enables robust knowledge curation in multi-agent systems despite adversarial agents.