# Accelerating Large Language Model Reasoning via Speculative Search

arXiv: https://arxiv.org/abs/2505.02865 · HTML: https://mlsanity.com/paper/2505.02865/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 3 May 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

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

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (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)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search](https://mlsanity.com/paper/2406.03816/) (2024)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Efficient Large Language Models: A Survey](https://mlsanity.com/paper/2312.03863/) (2023)
- [AlphaMath Almost Zero: Process Supervision without Process](https://mlsanity.com/paper/2405.03553/) (2024)
- [OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models](https://mlsanity.com/paper/2410.09671/) (2024)
- [Cascade Speculative Drafting for Even Faster LLM Inference](https://mlsanity.com/paper/2312.11462/) (2023)
- [CLLMs: Consistency Large Language Models](https://mlsanity.com/paper/2403.00835/) (2024)
- [Interpretable Contrastive Monte Carlo Tree Search Reasoning](https://mlsanity.com/paper/2410.01707/) (2024)
- [TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling](https://mlsanity.com/paper/2410.16033/) (2024)
- [Enhancing LLM Reasoning with Reward-guided Tree Search](https://mlsanity.com/paper/2411.11694/) (2024)
- [MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time](https://mlsanity.com/paper/2405.16265/) (2024)
- [Multi-Candidate Speculative Decoding](https://mlsanity.com/paper/2401.06706/) (2024)
- [RoT: Enhancing Large Language Models with Reflection on Search Trees](https://mlsanity.com/paper/2404.05449/) (2024)
- [SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding](https://mlsanity.com/paper/2406.18200/) (2024)
- [Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models](https://mlsanity.com/paper/2404.14897/) (2024)
- [PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition](https://mlsanity.com/paper/2402.04838/) (2024)
- [S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs](https://mlsanity.com/paper/2405.20314/) (2024)

## Built on by (most cited first, 16 of 16)

- [Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models](https://mlsanity.com/paper/2508.02120/) (2025)
- [Speculative Actions: A Lossless Framework for Faster Agentic Systems](https://mlsanity.com/paper/2510.04371/) (2025)
- [From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models](https://mlsanity.com/paper/2511.10788/) (2025)
- [A Survey on Parallel Reasoning](https://mlsanity.com/paper/2510.12164/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation](https://mlsanity.com/paper/2603.07416/) (2026)
- [SSR: Speculative Parallel Scaling Reasoning in Test-time](https://mlsanity.com/paper/2505.15340/) (2025)
- [Out-of-distribution Tests Reveal Compositionality in Chess Transformers](https://mlsanity.com/paper/2510.20783/) (2025)
- [Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models](https://mlsanity.com/paper/2511.18864/) (2025)
- [Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding](https://mlsanity.com/paper/2512.00805/) (2025)
- [From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models](https://mlsanity.com/paper/2601.15690/) (2026)
- [TIGER: Text-Conditioned Visual Gated Routing with Acceptance Alignment for Multimodal Speculative Decoding](https://mlsanity.com/paper/2607.11131/) (2026)
- [Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models](https://mlsanity.com/paper/2510.23334/) (2025)
- [ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning](https://mlsanity.com/paper/2608.21860/) (2026)
- [Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning](https://mlsanity.com/paper/2606.30217/) (2026)
- [Trajectory-Retrieval Speculative Decoding: When Does a Model's Own History Help?](https://mlsanity.com/paper/2610.07350/) (2026)

## Abstract (arXiv)

Tree-search-based reasoning methods have significantly enhanced the reasoning capability of large language models (LLMs) by facilitating the exploration of multiple intermediate reasoning steps, i.e., thoughts. However, these methods suffer from substantial inference latency, as they have to generate numerous reasoning thoughts, severely limiting LLM applicability. To address this challenge, we propose a novel Speculative Search (SpecSearch) framework that significantly accelerates LLM reasoning by optimizing thought generation. Specifically, SpecSearch utilizes a small model to strategically collaborate with a large model at both thought and token levels, efficiently generating high-quality reasoning thoughts. The major pillar of SpecSearch is a novel quality-preserving rejection mechanism, which effectively filters out thoughts whose quality falls below that of the large model's outputs. Moreover, we show that SpecSearch preserves comparable reasoning quality to the large model. Experiments on both the Qwen and Llama models demonstrate that SpecSearch significantly outperforms state-of-the-art approaches, achieving up to 2.12× speedup with comparable reasoning quality.