BaRe-Mem uses Bayesian reliability memory to shift a central model toward autonomous reasoning as advice turns misleading, and finds capable workers earlier on MuSiQue
The work introduces BaRe-Mem, an online Bayesian reliability memory that estimates advisor reliability conditioned on the central model's internal belief representations, uses those estimates to modulate attention and to decide whether to consult; across nine benchmarks and six central models it is more robust to misleading advisor information than debate and majority voting, stays above autonomous reasoning on the more challenging tasks across all tested misleading levels, and in MuSiQue agent-team routing identifies capable workers earlier than routing by historical success counts.