# SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications

arXiv: https://arxiv.org/abs/2411.04975 · HTML: https://mlsanity.com/paper/2411.04975/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 29 of 29)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [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)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding](https://mlsanity.com/paper/2402.12374/) (2024)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)
- [Inference with Reference: Lossless Acceleration of Large Language Models](https://mlsanity.com/paper/2304.04487/) (2023)
- [Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling](https://mlsanity.com/paper/2408.08696/) (2024)
- [TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput](https://mlsanity.com/paper/2406.14066/) (2024)
- [Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding](https://mlsanity.com/paper/2404.08698/) (2024)

## Built on by (most cited first, 30 of 36)

- [History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL](https://mlsanity.com/paper/2508.18588/) (2025)
- [Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning](https://mlsanity.com/paper/2511.14617/) (2025)
- [Speculative Speculative Decoding](https://mlsanity.com/paper/2603.03251/) (2026)
- [JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting](https://mlsanity.com/paper/2606.18394/) (2026)
- [Beat the long tail: Distribution-Aware Speculative Decoding for RL Training](https://mlsanity.com/paper/2511.13841/) (2025)
- [Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding](https://mlsanity.com/paper/2512.01278/) (2025)
- [Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling](https://mlsanity.com/paper/2509.04474/) (2025)
- [SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference](https://mlsanity.com/paper/2607.03333/) (2026)
- [Shift Parallelism: Low-Latency, High-Throughput LLM Inference for Dynamic Workloads](https://mlsanity.com/paper/2509.16495/) (2025)
- [SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache](https://mlsanity.com/paper/2601.09083/) (2026)
- [SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification](https://mlsanity.com/paper/2510.02329/) (2025)
- [Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs](https://mlsanity.com/paper/2512.20573/) (2025)
- [TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling](https://mlsanity.com/paper/2608.10402/) (2026)
- [When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding](https://mlsanity.com/paper/2511.01282/) (2025)
- [WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning](https://mlsanity.com/paper/2607.17299/) (2026)
- [JuDi: Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence](https://mlsanity.com/paper/2601.04766/) (2026)
- [Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding](https://mlsanity.com/paper/2604.02047/) (2026)
- [BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning](https://mlsanity.com/paper/2605.08862/) (2026)
- [TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts](https://mlsanity.com/paper/2608.22788/) (2026)
- [MineDraft: A Framework for Batch Parallel Speculative Decoding](https://mlsanity.com/paper/2603.18016/) (2026)
- [PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding](https://mlsanity.com/paper/2605.15609/) (2026)
- [WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing](https://mlsanity.com/paper/2606.07710/) (2026)
- [AgentSpec: Speculative Decoding for Batch Inference of LLM Agents](https://mlsanity.com/paper/2608.24004/) (2026)
- [Margins, Not Windows: Training-Free Per-Step Lossy Speculative Decoding](https://mlsanity.com/paper/2609.02897/) (2026)
- [OWL: Overcoming Window Length-Dependence in Speculative Decoding for Long-Context Inputs](https://mlsanity.com/paper/2510.07535/) (2025)
- [Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding](https://mlsanity.com/paper/2606.01019/) (2026)
- [DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs](https://mlsanity.com/paper/2607.28848/) (2026)
- [Self-Speculation for Faster Reasoning Models](https://mlsanity.com/paper/2608.20359/) (2026)
- [GRAFT: Adaptive DLM-Based Draft Tree Construction with Target-Distilled Edge Scoring](https://mlsanity.com/paper/2608.20375/) (2026)
- [Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems](https://mlsanity.com/paper/2608.24650/) (2026)

## Abstract (arXiv)

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present unique workload characteristics: instead of diverse independent requests, agentic frameworks typically submit repetitive inference requests, such as multi-agent pipelines performing similar subtasks or self-refinement loops iteratively enhancing outputs. These workloads result in long and highly predictable sequences, which current speculative decoding methods do not effectively exploit. To address this gap, we introduce SuffixDecoding, a novel method that utilizes efficient suffix trees to cache long token sequences from prompts and previous outputs. By adaptively speculating more tokens when acceptance likelihood is high and fewer when it is low, SuffixDecoding effectively exploits opportunities for longer speculations while conserving computation when those opportunities are limited. Evaluations on agentic benchmarks, including SWE-Bench and Text-to-SQL, demonstrate that SuffixDecoding achieves speedups of up to 5.3×, outperforming state-of-the-art methods -- 2.8× faster than model-based approaches like EAGLE-2/3 and 1.9× faster than model-free approaches such as Token Recycling. SuffixDecoding is open-sourced at https://github.com/snowflakedb/ArcticInference