LATIDIA · Investigación

Aprendizaje colaborativo y razonamiento sobre rebanadas modelo

arXiv: 2610.12927v1Tipo de anuncio: nuevo Resumen: los modelos de lenguaje grandes (LLM) sobresalen en diversas tareas, beneficiándose de los conocimientos previos, el razonamiento en contexto y el cálculo del tiempo de prueba. A pesar de estas fortalezas, solo

La noticia

arXiv:2610.12927v1 Announce Type: new Abstract: Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite these strengths, single-model reasoning remains vulnerable to error propagation, as later steps depend on the model's earlier outputs, leaving reasoning blind spots difficult to independently reassess. To address this limitation, we develop \textit{collaborative learning}, encompassing the construction of heterogeneous collaborators and the learning of effective cross-model collaboration. Specifically, \textit{model slicing} replaces a large model with smaller, heterogeneous models under a comparable parameter budget, enabling prior reasoning to be reassessed across distinct model parameterizations. \textit{Pyramid supervision} combines protocol distillation with step-level supervision to refine reasoning and interaction decisions