SOURCE-LINKED INTELLIGENCE

Compositional Reasoning in Language Models under Reinforcement Learning Post-Training

arXiv · Artificial Intelligence · article · Sep 16, 2026 · UTC

Compositional reasoning is critical for real-world problem solving: since training data is necessarily limited, models must generalize by composing learned skills in new ways. While post-training methods such as reinforcement learning (RL) have substantially improved the reasoning abilities of language models (LMs), their effects on compositional reasoning remain less well understood. We propose a dependency-graph framework to formalize compositional reasoning, yielding three levels of compositionality with increasing complexity. Empirically, we instantiate this framework with data-structure t

Read original source ↗ Open in workspace

recordType

paper

region

Global