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

arXiv: https://arxiv.org/abs/2608.00814 · HTML: https://mlsanity.com/paper/2608.00814/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 16 of 16)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [DFlash: Block Diffusion for Flash Speculative Decoding](https://mlsanity.com/paper/2602.06036/) (2026)
- [Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling](https://mlsanity.com/paper/2408.08696/) (2024)
- [SAM Decoding: Speculative Decoding via Suffix Automaton](https://mlsanity.com/paper/2411.10666/) (2024)
- [PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative Decoding](https://mlsanity.com/paper/2605.08632/) (2026)
- [ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding](https://mlsanity.com/paper/2604.13519/) (2026)
- [Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States](https://mlsanity.com/paper/2602.03708/) (2026)

## Built on by (most cited first, 1 of 1)

- [LEAP: Learning Efficient Action Proposals For LLM Agents](https://mlsanity.com/paper/2610.02670/) (2026)

## Abstract (arXiv)

LLMs generate tool calls token by token, even though the function choice and argument values can often be predicted in parallel from the request and tool schema. ToolSpec reduces this cost by drafting schema tokens and retrieving earlier calls, but cannot propose request-specific values absent from either source. We present OoO-Spec, which computes these missing semantics out of order. At request arrival, a Qwen3-0.6B sidecar predicts the function choice and all schema-defined argument slots in one parallel request-level wave while the target begins ToolSpec decoding. The runtime joins the slot values, renders the resulting call as text, and exposes it to subsequent candidate-construction rounds. The target polls without blocking, re-tokenizes a ready hint with its own tokenizer, and remains the sole verifier and commit authority. The sidecar is trained once with LoRA on Qwen2.5-32B teacher traces and used unchanged across Qwen2.5, Qwen3, and Llama targets, without target-specific drafter training. Across seven fully ranked targets and three benchmarks under greedy batch-one decoding, OoO-Spec is fastest among all evaluated methods in all 21 target-benchmark cells, reaching 2.46x-5.34x over autoregressive decoding with an unweighted mean of 3.89x, versus 2.95x for ToolSpec. It also outperforms every evaluated released learned drafter in each comparable cell. Across Qwen3-4B, 8B, 14B, and 32B targets, the same sidecar improves on ToolSpec by 34.1% on average. Its compact semantic payload averages 85 bytes per request excluding protocol metadata, supporting effective split-GPU overlap.