AI RESEARCH

Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Environments

arXiv CS.LG

ArXi:2510.04142v2 Announce Type: replace-cross This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic biases and drift to the target model. To address this, we formulate multi-source reasoning alignment as a constraint satisfaction problem under concept drift theory.