RESEARCHInvestigateNEXT 12 MONTHS
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers propose a verifier-free breadth-depth refinement framework for LLM test-time scaling, reducing reliance on external reward models.
Open source