arXiv 2610.30882 · cs.LG · 2026-10-22
Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
Zhizhuo Kou, Sizai Hou, Long Chen, Jian Yang, Junyu Luo, Jingshu Peng, Wenkai Zhang, Sirui Han and 1 more
HUAWEI Noah's Ark Lab
One-line takeaway
The 'wait' instruction is inherited from training data, not invented by RL; its presence correlates with base model exposure, not RL training.
研究发现‘wait’指令并非RL训练新产生，而是源于训练数据继承；RL在提升准确率的同时并未新增该标记，其出现与模型基础架构和训练过程密切相关。
Quick look: the first sentence of the official arXiv abstract (Chinese is machine-translated). Key points are being written; read the original for details.
Read on arXiv PDF Hugging Face discussion Code
Topics & disciplines
More on Reinforcement learning
- Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation ▲214
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight ▲189
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches ▲152
- Sharpening Tax in Post-Training ▲111
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
More on Reasoning
- LoopVL: Recurrent Visual Intelligence 2026-09-29 · ▲417
- LEV: Thinking Fast and Deep with Looped Decision Models 2026-10-14 · ▲337
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence 2026-09-28 · ▲224
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics 2026-09-28 · ▲205
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.