activity
20242026
most citedMulti-agent Reinforcement Learning-based In-place Scaling Engine for Edge-cloud Systems

4 citations · 5 across the 10 of their papers we have counts for

collaborators
Showing cs.MAShow all

1 paper · 1 filter

cs.MA2026

The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate

Blaž Bertalanič, Carolina Fortuna

Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review filters hallucinations. Yet th…