Source record

Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2609.11709.

Pipeline notes

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

The paper proposes Bayesian backward reasoning as a label-free anchor for multi-agent LLM decision-making when agents disagree. It constructs reverse posteriors via explicit likelihoods, uses Jensen-Shannon divergence to measure cross-path consistency, and offers three strategies (MinJS, FwdJS, LogLin) evaluated on DDXPlus across five LLM backbones, with LogLin performing best on disagreement-heavy subsets.

First concrete cross-factorization method for resolving multi-agent LLM disagreement without labels, with reproducible strategies and measured gains on the disagreement subset.

Cited by

No citations on record.