📑 arXiv 3d ago
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
SpecGuard performs step-level verification in speculative decoding using only model-internal signals (attention-based grounding scores and ensemble verification) without external reward models. Prevents erroneous reasoning steps from propagating while avoiding the latency and computational overhead of external verifiers in multi-step reasoning tasks.