From Evidence to Action: MAS Prediction and Decision for Low-Probability Events

Predicting low-probability events requires both preserving the order of magnitude of probabilities and identifying evidence dependencies and executing actions aligned with the specified loss objective. Existing evaluations of Multi-Agent System (MAS) prediction and collaboration rarely distinguish communication gains, information propagation, and action execution within a single task, and building agents from the same foundation model further limits what can be inferred about cross-model collaboration. We propose a paired framework benchmarked against computable conditional probabilities. In a virtual public-service scenario, we manipulate source relationships and the disclosure of private records and structural information, and use a new decision branch to separate probability substitution from action execution. We use four models to form Homogeneous MAS, which jointly constitute a Hybrid MAS where each virtual world uses four balanced compositions and two decoding runs, and all experiments are repeated on the same worlds. In the main experiment over 128 worlds, ordinary communication relative to independent ensembling yields a mean absolute ${\log }_{10}$ error difference of $-0.0152$ in the Homogeneous MAS and $-0.01402$ in the Hybrid MAS. After two rounds of communication, the availability rate of valid private raw records for ordinary communication and source verification in the Hybrid MAS approaches 84%. Through paired replication across compositions, verifiable information channels, and public loss objectives, this study shows that group consensus, probability accuracy, and action optimality require separate evaluation benchmarks.