Agent skill · research science · davila7
nowait-reasoning-optimizer
Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.
Why this skill is useful
Adds a custom logit processor script that optimizes reasoning efficiency in R1-style LLMs, significantly reducing token usage during inference.
What it needs
Requires transformers, vllm installed locally. About 2k tokens when loaded. Last updated 2026-08-06. 30,138 stars on the source repository.
What this skill does
NOWAIT Reasoning Optimizer Implements the NOWAIT technique from the paper "Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency" (Wang et al., 2025). Overview NOWAIT is a training-free inference-time intervention that suppresses self-reflection tokens (e.g., "Wait", "Hmm", "Alternatively") during generation, reducing chain-of-thought (CoT) trajectory length by 27-51% without compromising model utility. When to Use Deploying R1-style reasoning models with limited compute Reducing inference latency for production systems Optimizing token costs for reasoning tasks Working with verbose CoT outputs that need streamlining Supported Models Model Series Type Token Reduction -------------- ------ ----------------- QwQ-32B RL-based 16-31% Phi4-Reasoning-Plus RL-based 23-28% Qwen3-32B RL-based 13-16% Kimi-VL-A3B Multimodal 40-60% QvQ-72B-Preview Multimodal 20-30% Important: NOWAIT works best with RL-based models. Distilled models (Qwen3-4B/8B/14B) show degraded performance when reflection tokens are suppressed. Quick Start 1. Basic Implementation 2. Keywords Suppressed See references/keywords.md for the complete list. Core keywords: How It Works 1. Initialize Keywords: Identify reflection keywords from empirical analysis 2. Expand to Token Variants: Map keywords to all token variants in vocabulary (e.g., "wait" → " wait", "Wait", " Wait", ".wait", "WAIT") 3. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills davila7/nowait