DesDD: A Design-Enabled Framework with Dual-Layer Debugging for LLM-based Iterative API Orchestrating
In modern software engineering (SE), coordinated API calls are essential for complex data retrieval and processing tasks. Large Language Models (LLMs) provide promising capabilities for natural language parsing and task automation, inspiring research into integrating APIs orchestration with LLMs. However, while existing LLM-based frameworks have made notable strides, they face challenges with complex tasks that often require iterative, stepwise problem-solving. Current frameworks lack structured guidance, relying on LLMs’ own capabilities, leading to blind iterations, inefficient error correction, and inefficient token utilization. This work introduces DesDD (\underline{Des}ign-enabled framework with \underline{D}ual-layer \underline{D}ebugging), a structured framework for iterative API orchestration driven by LLMs. Inspired by software engineering design principles, DesDD organizes the API orchestration workflow into distinct design and coding phases. The dual-layer debugging mechanism enhances error detection and correction across both phases, improving reliability and efficiency in the orchestration process. DesDD provides a structured \emph{design-first, then-code} pathway, allowing LLMs to solve tasks iteratively with a well-defined, stepwise approach that systematically guides each stage of problem-solving. The equipped dual-layer debugging component provides hierarchical error detection at both the design and coding aspects, enabling targeted corrections. This framework not only improves the robustness of the system, increases the success rate of error correction, but also improves the token utilization efficiency in the iterative process. Comprehensive experiments demonstrate that DesDD outperforms existing frameworks in orchestration efficiency and accuracy, with significantly reduced token usage. DesDD provides an effective LLM-based solution for API orchestration in complex tasks, moreover, its application of SE design principles demonstrates inherent generalizability, which shows a valuable pathway for LLM-driven automated complex task resolution across diverse scenarios.
Sat 21 JunDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
11:00 - 13:00 | Session7: AI for Software Engineering IIIResearch Track at Cosmos 3C Chair(s): Lina Gong Nanjing University of Aeronautics and Astronautic | ||
11:00 15mTalk | Brevity is the Soul of Wit: Condensing Code Changes to Improve Commit Message Generation Research Track Hongyu Kuang Nanjing University, Ning Zhang Nanjing University, Hui Gao Nanjing University, Xin Zhou Nanjing University, Wesley Assunção North Carolina State University, Xiaoxing Ma Nanjing University, Dong Shao Nanjing University, Guoping Rong Nanjing University, He Zhang Nanjing University | ||
11:15 15mTalk | DesDD: A Design-Enabled Framework with Dual-Layer Debugging for LLM-based Iterative API Orchestrating Research Track Zhuo Cheng Jiangxi normal University, Zhou Zou Jiangxi Normal University, Qing Huang School of Computer Information Engineering, Jiangxi Normal University, Zhenchang Xing CSIRO's Data61, Wei Zhang Jiangxi Meteorological Disaster Emergency Early Warning Center, Jiangxi Meteorological Bureau, Shaochen Wang Jiangxi Normal Univesity, Xueting Yi Jiangxi Meteorological Disaster Emergency Early Warning Center, Jiangxi Meteorological Bureau, Huan Jin School of Information Engineering, Jiangxi University of Technology, Zhiping Liu College of Information Engineering, Gandong University, Zhaojin Lu Jiangxi Tellhow Animation College, Tellhow Group Co.,LTD | ||
11:30 15mTalk | AUCAD: Automated Construction of Alignment Dataset from Log-Related Issues for Enhancing LLM-based Log Generation Research Track Hao Zhang Nanjing University, Dongjun Yu Nanjing University, Lei Zhang Nanjing University, Guoping Rong Nanjing University, YongdaYu Nanjing University, Haifeng Shen Southern Cross University, He Zhang Nanjing University, Dong Shao Nanjing University, Hongyu Kuang Nanjing University | ||
11:45 15mTalk | Enhancement Report Approval Prediction: A Comparative Study of Large Language Models Research Track | ||
12:00 15mTalk | MetaCoder: Generating Code from Multiple Perspectives Research Track chen xin , Zhijie Jiang National University of Defense Technology, Yong Guo National University of Defense Technology, Zhouyang Jia National University of Defense Technology, Si Zheng National University of Defense Technology, Yuanliang Zhang National University of Defense Technology, Shanshan Li National University of Defense Technology | ||
12:15 15mTalk | API-Repo: API-centric Repository-level Code Completion Research Track Zhihao Li State Key Laboratory for Novel Software and Technology, Nanjing University, Chuanyi Li Nanjing University, Changan Niu Software Institute, Nanjing University, Ying Yan State Key Laboratory for Novel Software and Technology, Nanjing University, Jidong Ge Nanjing University, Bin Luo Nanjing University | ||
12:30 15mTalk | AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT Length Research Track Junhang Cheng Beihang University, Fang Liu Beihang University, Chengru Wu Beihang University, Li Zhang Beihang University Pre-print Media Attached File Attached | ||
12:45 15mTalk | Lightweight Probabilistic Coverage Metrics for Efficient Testing of Deep Neural Networks Research Track Yining Yin Nanjing University, Yang Feng Nanjing University, Shihao Weng Nanjing University, Xinyu Gao , Jia Liu Nanjing University, Zhihong Zhao Nanjing University | ||
Cosmos 3C is the third room in the Cosmos 3 wing.
When facing the main Cosmos Hall, access to the Cosmos 3 wing is on the left, close to the stairs. The area is accessed through a large door with the number “3”, which will stay open during the event.