ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification

Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces.Steplevel speculative reasoning aims to mitigate this cost, yet existing approaches face a longstanding trade-off among accuracy, inference speed, and resource efficiency.We propose ConfSpec, a confidence-gated cascaded verification framework that resolves this trade-off.Our key insight is an asymmetry between generation and verification: while generating a correct reasoning step requires substantial model capacity, step-level verification is a constrained discriminative task for which small draft models are well-calibrated within their competence range, enabling high-confidence draft decisions to be accepted directly while selectively escalating uncertain cases to the large target model.Evaluation across diverse workloads shows that ConfSpec achieves up to 2.24× end-to-end speedups while matching target-model accuracy.Our method requires no external judge models and is orthogonal to token-level speculative decoding, enabling further multiplicative acceleration.