# Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents

arXiv: https://arxiv.org/abs/2505.12065 · HTML: https://mlsanity.com/paper/2505.12065/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 17 May 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 27 of 27)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion](https://mlsanity.com/paper/2405.16444/) (2024)
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024)
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025)
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [Re2G: Retrieve, Rerank, Generate](https://mlsanity.com/paper/2207.06300/) (2022)
- [RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.12457/) (2024)
- [A Survey on Retrieval-Augmented Text Generation for Large Language Models](https://mlsanity.com/paper/2404.10981/) (2024)
- [A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions](https://mlsanity.com/paper/2410.12837/) (2024)
- [TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text](https://mlsanity.com/paper/2410.07590/) (2024)
- [InferCept: Efficient Intercept Support for Augmented Large Language Model Inference](https://mlsanity.com/paper/2402.01869/) (2024)
- [Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution](https://mlsanity.com/paper/2406.00059/) (2024)
- [Compressing Long Context for Enhancing RAG with AMR-based Concept Distillation](https://mlsanity.com/paper/2405.03085/) (2024)
- [Accelerating Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.15246/) (2024)
- [AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.19251/) (2024)
- [Randomized partition trees for exact nearest neighbor search](https://mlsanity.com/paper/1302.1948/) (2013)
- [Fast Inference for Augmented Large Language Models](https://mlsanity.com/paper/2410.18248/) (2024)
- [Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning](https://mlsanity.com/paper/2502.08056/) (2025)

## Built on by (most cited first, 5 of 5)

- [Deep Research: A Survey of Autonomous Research Agents](https://mlsanity.com/paper/2508.12752/) (2025)
- [SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution](https://mlsanity.com/paper/2605.10114/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models](https://mlsanity.com/paper/2506.08352/) (2025)
- [Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents](https://mlsanity.com/paper/2607.05690/) (2026)

## Abstract (arXiv)

Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved paradigm introduces substantial efficiency bottlenecks. First, we observe that both highly accurate and overly approximate retrieval methods degrade system efficiency: exact search incurs significant retrieval overhead, while coarse retrieval requires additional reasoning steps during generation. Second, we identify inefficiencies in system design, including improper scheduling and frequent retrieval stalls, which lead to cascading latency -- where even minor delays in retrieval amplify end-to-end inference time. To address these challenges, we introduce SearchAgent-X, a high-efficiency inference framework for LLM-based search agents. SearchAgent-X leverages high-recall approximate retrieval and incorporates two key techniques: priority-aware scheduling and non-stall retrieval. Extensive experiments demonstrate that SearchAgent-X consistently outperforms state-of-the-art systems such as vLLM and HNSW-based retrieval across diverse tasks, achieving up to 3.4× higher throughput and 5× lower latency, without compromising generation quality. SearchAgent-X is available at https://github.com/tiannuo-yang/SearchAgent-X.