AI RESEARCH
RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models
arXiv CS.CL
•
ArXi:2603.27008v1 Announce Type: new Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have nstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, their performance remains highly sensitive to prompt formulation, and designing effective prompts is typically a manual and iterative process that does not scale well across tasks or domains. To address this limitation, we