# Reinforcement Speculative Decoding for Fast Ranking

arXiv: https://arxiv.org/abs/2505.20316 · HTML: https://mlsanity.com/paper/2505.20316/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving.
- Builds on 42 of its 49 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- Efficient LLM inference and serving / [Speculative decoding](https://mlsanity.com/inference/speculative-decoding/)

## Builds on (most cited first, 30 of 42)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [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)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [DistillSpec: Improving Speculative Decoding via Knowledge Distillation](https://mlsanity.com/paper/2310.08461/) (2023)
- [Speculative Decoding with Big Little Decoder](https://mlsanity.com/paper/2302.07863/) (2023)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [Accelerating LLM Inference with Staged Speculative Decoding](https://mlsanity.com/paper/2308.04623/) (2023)
- [REST: Retrieval-Based Speculative Decoding](https://mlsanity.com/paper/2311.08252/) (2023)
- [SpecTr: Fast Speculative Decoding via Optimal Transport](https://mlsanity.com/paper/2310.15141/) (2023)
- [Accelerating Transformer Inference for Translation via Parallel Decoding](https://mlsanity.com/paper/2305.10427/) (2023)
- [Online Speculative Decoding](https://mlsanity.com/paper/2310.07177/) (2023)
- [Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding](https://mlsanity.com/paper/2402.12374/) (2024)
- [Cascade Speculative Drafting for Even Faster LLM Inference](https://mlsanity.com/paper/2312.11462/) (2023)
- [GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding](https://mlsanity.com/paper/2402.02082/) (2024)
- [RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models](https://mlsanity.com/paper/2309.15088/) (2023)

## Built on by (most cited first, 3 of 3)

- [History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL](https://mlsanity.com/paper/2508.18588/) (2025)
- [Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation](https://mlsanity.com/paper/2508.18142/) (2025)
- [MMGRid: Navigating Temporal-aware and Cross-domain Generative Recommendation via Model Merging](https://mlsanity.com/paper/2601.15930/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have been widely adopted in ranking systems such as information retrieval (IR) systems and recommender systems (RSs). To alleviate the latency of auto-regressive decoding, some studies explore the single (first) token decoding for ranking approximation, but they suffer from severe degradation in tail positions. Although speculative decoding (SD) methods can be a remedy with verification at different positions, they face challenges in ranking systems due to their left-to-right decoding paradigm. Firstly, ranking systems require strict latency constraints, but verification rounds in SD methods remain agnostic; Secondly, SD methods usually discard listwise ranking knowledge about unaccepted items in previous rounds, hindering future multi-token prediction, especially when candidate tokens are the unaccepted items. In this paper, we propose a Reinforcement Speculative Decoding method for fast ranking inference of LLMs. To meet the ranking systems' latency requirement, we propose an up-to-down decoding paradigm that employs an agent to iteratively modify the ranking sequence under a constrained budget. Specifically, we design a ranking-tailored policy optimization, actively exploring optimal multi-round ranking modification policy verified by LLMs via reinforcement learning (RL). To better approximate the target LLM under the constrained budget, we trigger the agent fully utilizing the listwise ranking knowledge about all items verified by LLMs across different rounds in RL, enhancing the modification policy of the agent. More importantly, we demonstrate the theoretical robustness and advantages of our paradigm and implementation. Experiments on both IR and RS tasks show the effectiveness of our proposed method.