OoO-Spec: Out-of-Order Semantic Speculation for Fast Tool Calling

arXiv:2608.00814 · cs.CL · Submitted 2026-08-01 · Read on arXiv

Zhiheng Zhang, Mujie Xu, Feiyu Sun, Zhixin Zhang

cs.CL

Submitted: 2026-08-01

Comments: 10 pages, 4 figures, 6 tables; supplementary material included

Code: https://github.com/apoorvumang/prompt-lookupdecoding

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

Terminology

• Benchmark — 13× in this paper · explained in 2 episodes
• Verification — 10× in this paper · explained in 2 episodes
• Speculative Decoding — 9× in this paper · explained in 2 episodes
• Transformer — 8× in this paper · explained in 2 episodes
• Transformers — 8× in this paper · explained in 2 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Verifier — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Token Recycling — 3× in this paper
• Decoder — 2× in this paper · explained in 2 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Prompt Lookup Decoding — 2× in this paper
• Tokenization — 2× in this paper · explained in 2 episodes
• Absorb — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Block Diffusion — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 5 episodes
• Scaffolding — 1× in this paper · explained in 3 episodes
• Weight Decay — 1× in this paper · explained in 2 episodes

Sources

• PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding
• Accelerating Large Language Model Decoding with Speculative Sampling
• Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
• SAM Decoding: Speculative Decoding via Suffix Automaton
• The Llama 3 Herd of Models
• Qwen2.5 Technical Report
• ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
• ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
• Qwen3 Technical Report

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