SOURCE-LINKED INTELLIGENCE

Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Reinforcement learning with verifiable rewards (RLVR) improves specific capabilities of large language models, but covering multiple capabilities often involves training separate domain experts and subsequently consolidating them. We organize three fusion paradigms by the artifacts they reuse: Merge combines expert task vectors, Mix RL pools their datasets, and multi-teacher on-policy distillation (MOPD) uses both. Because they have largely been studied in isolation, how they compare and how to choose among them remain unclear. We compare all three using shared experts and data across model sc

Read original source ↗ Open in workspace

recordType

paper

region

Global