works on
alignment 1collaborative AI 1dynamic preferences 1human-ai interaction 1social science integration 1

From the 1 of 8 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

The Consensus Trap: Rescuing Multi-Agent LLMs from Adversarial Majorities via Token-Level Collaboration

Jiayuan Liu, Shiyi Du, Weihua Du +2

Multi-agent large language model (LLM) architectures increasingly rely on response-level aggregation, such as Majority Voting (MAJ), to raise reasoning ceilings. However, in open e…