AI RESEARCH
When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
arXiv CS.AI
•
ArXi:2604.26649v1 Announce Type: cross Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains fundamentally misaligned. Current RAG systems optimize for providing context before reasoning begins, while reasoning models require evidence injection during multi-step inference chains. We