Source record

Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2609.27822.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

An audit of confidence-routed multi-agent broadcast protocols across 4,181 olympiad-math traces and a 2-by-2 model/benchmark grid finds that routing discrimination, probability calibration, and public commitment are three distinct properties that must be measured separately before raw-confidence routing is deployed, as fixed routers and cross-fitted calibration do not recover missing discrimination in the Gemma cells.

Concrete trace-level evidence with specific numbers that the popular 'highest-confidence agent speaks next' pattern is more fragile across models and tasks than its adoption suggests.

Cited by

No citations on record.