arXiv Artificial Intelligence

Compositional Reasoning in Language Models under Reinforcement Learning Post-Training

3 hours ago 18.09.2026 07:00 👁 2 views
Compositional Reasoning in Language Models under Reinforcement Learning Post-Training

Quick summary

arXiv:2609.19465v1 Announce Type: new Abstract: 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

Key takeaways

  • arXiv:2609.19465v1 Announce Type: new Abstract: 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.

Why it matters

This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗