SAC is a decentralized iterative filter-and-refine protocol that achieves (F+1)-robustness in LLM multi-agent systems, suppressing Byzantine influence and improving performance on reasoning benchmarks where prior methods fail.
Lynch, Shlomit S
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1