Cover Image

From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Purohit, Kiran, Narayanam, Ramasuri, Pal, Soumyabrata
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification
by: Bai, Tianyi, et al.
Published: (2025)

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification
by: Liu, Siran, et al.
Published: (2026)

Evaluating Step-by-Step Reasoning through Symbolic Verification
by: Zhang, Yi-Fan, et al.
Published: (2022)

TALON: Confidence-Aware Speculative Decoding with Adaptive Token Trees
by: Liu, Tianyu, et al.
Published: (2026)

Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning
by: Vladika, Juraj, et al.
Published: (2025)

Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
by: Dong, Ximing, et al.
Published: (2026)

Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding
by: Pan, Lehan, et al.
Published: (2026)

Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
by: Kim, Sungkyun, et al.
Published: (2025)

Sparse Linear Bandits with Blocking Constraints
by: Jain, Adit, et al.
Published: (2024)

Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
by: Ziashahabi, Amir, et al.
Published: (2025)

ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
by: Fan, Ziqing, et al.
Published: (2025)

Accelerate Speculative Decoding with Sparse Computation in Verification
by: Wang, Jikai, et al.
Published: (2025)

Uncertainty-Aware Step-wise Verification with Generative Reward Models
by: Ye, Zihuiwen, et al.
Published: (2025)

SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
by: Lin, Yijun, et al.
Published: (2026)

Traversal Verification for Speculative Tree Decoding
by: Weng, Yepeng, et al.
Published: (2025)

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
by: Su, Xin, et al.
Published: (2026)

Reward-Guided Speculative Decoding for Efficient LLM Reasoning
by: Liao, Baohao, et al.
Published: (2025)

First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning
by: Jain, Kushal, et al.
Published: (2023)

Entropy-Aware Speculative Decoding Toward Improved LLM Reasoning
by: Su, Tiancheng, et al.
Published: (2025)

RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step
by: Luo, Xiaocheng, et al.
Published: (2026)

CAFIN: Centrality Aware Fairness inducing IN-processing for Unsupervised Representation Learning on Graphs
by: Arun, Arvindh, et al.
Published: (2023)

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
by: Wang, Jikai, et al.
Published: (2025)

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
by: Nie, Shuo, et al.
Published: (2026)

Multi-Candidate Speculative Decoding
by: Yang, Sen, et al.
Published: (2024)

Multi-Step Reasoning in Korean and the Emergent Mirage
by: Son, Guijin, et al.
Published: (2025)

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
by: Mishra, Venkatesh, et al.
Published: (2025)

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation
by: Liu, Tianyu, et al.
Published: (2025)

Block Verification Accelerates Speculative Decoding
by: Sun, Ziteng, et al.
Published: (2024)

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding
by: Hu, Shijing, et al.
Published: (2025)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
by: Yang, Penghui, et al.
Published: (2025)

Scaling Speculative Decoding with Lookahead Reasoning
by: Fu, Yichao, et al.
Published: (2025)

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models
by: Wu, Canhui, et al.
Published: (2025)

Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR
by: Hsu, Chan-Jan, et al.
Published: (2024)

Improving Multi-candidate Speculative Decoding
by: Lu, Xiaofan, et al.
Published: (2024)

What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning
by: Ferrao, Jeremias, et al.
Published: (2025)

Training-free Dropout Sampling for Semantic Token Acceptance in Speculative Decoding
by: Lee, Jeongtae, et al.
Published: (2026)

Multi-Step Semantic Reasoning in Generative Retrieval
by: Dong, Steven, et al.
Published: (2026)

RAISE: Enhancing Scientific Reasoning in LLMs via Step-by-Step Retrieval
by: Oh, Minhae, et al.
Published: (2025)

Cost-Aware Diffusion Draft Trees for Speculative Decoding
by: Zhang, Shuai, et al.
Published: (2026)

SPEED: Speculative Pipelined Execution for Efficient Decoding
by: Hooper, Coleman, et al.
Published: (2023)