AI RESEARCH
CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
arXiv CS.CL
•
ArXi:2506.11077v3 Announce Type: replace Large reasoning models (LRMs), such as OpenAI's o1 and DeepSeek-R1, harness test-time scaling to perform multi-step reasoning for complex problem-solving. This reasoning process, executed before producing final answers, is often guided by special juncture tokens that prompt self-evaluative reflection. These transition markers and reflective cues are referred to as "reflection tokens" (e.g., "wait", "but", "alternatively"). In this work, we treat reflection tokens as a "resource" and.