TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding

arXiv:2610.20175 · cs.CL · Submitted 2026-10-14 · Read on arXiv

cs.CL

Submitted: 2026-10-14

Updated: 2026-10-14

Code: https://github.com/Robot2050/TreeSpark

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Speculative Decoding — 1× in this paper · explained in 2 episodes

Sources

• Program Synthesis with Large Language Models
• Accelerating Large Language Model Decoding with Speculative Sampling
• DFlash: Block Diffusion for Flash Speculative Decoding
• Evaluating Large Language Models Trained on Code
• DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
• Training Verifiers to Solve Math Word Problems
• Measuring Coding Challenge Competence With APPS
• Measuring Mathematical Problem Solving With the MATH Dataset
• JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
• Efficient Memory Management for Large Language Model Serving with PagedAttention
• Competition-Level Code Generation with AlphaCode
• Let's Verify Step by Step
• SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
• Accelerating Speculative Decoding with Block Diffusion Draft Trees
• TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
• Qwen3 Technical Report
• Cost-Aware Diffusion Draft Trees for Speculative Decoding
• Writer-R1: Dynamic Rubric Mining for Reinforcement Learning of Open-Ended Writing
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering