SlsReuse: LLM-Powered Serverless Function Reuse

• URL: http://arxiv.org/abs/2511.17262v1
• Date: Fri, 21 Nov 2025 14:08:12 GMT
• Title: SlsReuse: LLM-Powered Serverless Function Reuse
• Authors: Jinfeng Wen, Yuehan Sun,
• Abstract summary: This paper presents SlsReuse, the first LLM-powered framework for serverless function reuse.<n>It learns unified semantic-enhanced representations of heterogeneous functions through effective prompt engineering.<n>Built on ChatGPT-4o, one of the most representative LLMs, SlsReuse achieves Recall@10 of 91.20%, exceeding the state-of-the-art baseline by 24.53 percentage points.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Serverless computing has rapidly emerged as a popular cloud computing paradigm. It enables developers to implement function-level tasks, i.e., serverless functions, without managing infrastructure. While reducing operational overhead, it poses challenges, especially for novice developers. Developing functions from scratch requires adapting to heterogeneous, platform-specific programming styles, making the process time-consuming and error-prone. Function reuse offers a promising solution to address these challenges. However, research on serverless computing lacks a dedicated approach for function recommendation. Existing techniques from traditional contexts remain insufficient due to the semantic gap between task descriptions and heterogeneous function implementations. Advances in large language models (LLMs), pre-trained on large-scale corpora, create opportunities to bridge this gap by aligning developer requirements with function semantics. This paper presents SlsReuse, the first LLM-powered framework for serverless function reuse. Specifically, SlsReuse first constructs a reusable function repository serving as a foundational knowledge base. Then, it learns unified semantic-enhanced representations of heterogeneous functions through effective prompt engineering with few-shot prompting, capturing implicit code intent, target platforms, programming languages, and cloud services. Finally, given a natural language task query, SlsReuse performs intent-aware discovery combined with a multi-level pruning strategy and similarity matching. We evaluate SlsReuse on a curated dataset of 110 task queries. Built on ChatGPT-4o, one of the most representative LLMs, SlsReuse achieves Recall@10 of 91.20%, exceeding the state-of-the-art baseline by 24.53 percentage points.

Related papers

• ReFuGe: Feature Generation for Prediction Tasks on Relational Databases with LLM Agents [33.930224200799366]
  ReFuGe is an agentic framework for generating predictive features on RDBs.<n>It operates within an iterative feedback loop until performance converges.<n> Experiments on RDB benchmarks demonstrate that ReFuGe substantially improves performance on various RDB prediction tasks.
  arXiv  Detail & Related papers  (2026-01-25T08:02:29Z)
• OpenLambdaVerse: A Dataset and Analysis of Open-Source Serverless Applications [0.6215404942415159]
  OpenLambdaVerse is a dataset of GitHub repositories that use the Serverless Framework in applications that contain one or more Lambda functions.<n>We gain important insights on the size and complexity of current applications, which languages and languages they employ, how are the functions triggered, the maturity of the projects, and their security practices.
  arXiv  Detail & Related papers  (2025-08-02T21:30:01Z)
• SweRank: Software Issue Localization with Code Ranking [109.3289316191729]
  SweRank is an efficient retrieve-and-rerank framework for software issue localization.<n>We construct SweLoc, a large-scale dataset curated from public GitHub repositories.<n>We show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems.
  arXiv  Detail & Related papers  (2025-05-07T19:44:09Z)
• Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling [6.102559098873098]
  Function calling is a complex task with widespread applications in domains such as information retrieval, software engineering and automation.<n>Large Language Models (LLMs) can automate this process but are computationally expensive and impractical in resource-constrained settings.<n>Small Language Models (SLMs) can operate efficiently, offering faster response times, and lower computational demands.
  arXiv  Detail & Related papers  (2025-04-27T15:26:51Z)
• Improving Small-Scale Large Language Models Function Calling for Reasoning Tasks [0.8425561594225592]
  This study introduces a novel framework for training smaller language models in function calling. It focuses on specific logical and mathematical reasoning tasks. The approach aims to improve performances of small-scale models for these tasks using function calling.
  arXiv  Detail & Related papers  (2024-10-24T16:27:35Z)
• Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks [35.97890508648945]
  We introduce the-20B-FUNCTIONCALLING model under an Apache 2.0 license. The model is trained using a multi-task training approach on seven fundamental tasks. We show that-20B-FUNCTIONCALLING has better generalizability on multiple tasks in seven different evaluation datasets.
  arXiv  Detail & Related papers  (2024-06-27T17:47:26Z)
• BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions [72.56339136017759]
  We introduce BigCodeBench, a benchmark that challenges Large Language Models (LLMs) to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks.<n>Our evaluation shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%.<n>We propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information.
  arXiv  Detail & Related papers  (2024-06-22T15:52:04Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Memory Sharing for Large Language Model based Agents [43.53494041932615]
  This paper introduces the Memory Sharing, a framework which integrates the real-time memory filter, storage and retrieval to enhance the In-Context Learning process. The experimental results demonstrate that the MS framework significantly improves the agents' performance in addressing open-ended questions.
  arXiv  Detail & Related papers  (2024-04-15T17:57:30Z)
• Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub [79.31134731122462]
  We introduce OpenAct benchmark to evaluate the open-domain task-solving capability, built on human expert consultation and repositories in GitHub.<n>We present OpenAgent, a novel LLM-based agent system that can tackle evolving queries in open domains through autonomously integrating specialized tools from GitHub.
  arXiv  Detail & Related papers  (2023-12-28T15:47:30Z)
• TaskWeaver: A Code-First Agent Framework [50.99683051759488]
  TaskWeaver is a code-first framework for building LLM-powered autonomous agents. It converts user requests into executable code and treats user-defined plugins as callable functions. It provides support for rich data structures, flexible plugin usage, and dynamic plugin selection.
  arXiv  Detail & Related papers  (2023-11-29T11:23:42Z)
• CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets [75.64181719386497]
  We present CRAFT, a tool creation and retrieval framework for large language models (LLMs) It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning.
  arXiv  Detail & Related papers  (2023-09-29T17:40:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.