Multi-Agent Consensus
Overview
Multi-agent consensus studies how autonomous systems influence one another to agree on beliefs, decisions, estimates, or coordinated actions. Methods range from graph-based consensus protocols and distributed control to voting, debate, confidence weighting, evidence checking, and adaptive communication. Applications include robot teams, distributed sensing, and groups of language models that deliberate or verify answers. A central tension is that agreement can speed coordination but does not guarantee correctness: shared errors, conformity, adversarial agents, and network structure can all make consensus unreliable.
Latest papers
133 papers10 papers in the last four weeks, down 57% on the four weeks before. 0.1% of all new papers.