AI RESEARCH
Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals
arXiv CS.LG
•
ArXi:2605.04236v1 Announce Type: new Large Language Model ensembles improve reasoning accuracy up to a performance boundary; beyond it, additional deliberation degrades accuracy. Static-budget methods cannot detect this boundary. Extended-thinking architectures compound the problem: a wrong answer after 120k tokens is indistinguishable from a correct one. We