Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents' performance, especially the functionality for agent topology, tools, and memory. However, current ADKs either lack sufficient functional support or rely on humans to manually design these components, limiting agents' generalizability and overall performance. We propose OpenSage, the first ADK that enables LLMs to automatically create agents with self-generated topology and toolsets while providing comprehensive and structured memory support. OpenSage offers effective functionality for agents to create and manage their own sub-agents and toolkits. It also features a hierarchical, graph-based memory system for efficient management and a specialized toolkit tailored to software engineering tasks. Extensive experiments across three state-of-the-art benchmarks with various backbone models demonstrate the advantages of OpenSage over existing ADKs. We also conduct rigorous ablation studies to demonstrate the effectiveness of our design for each component. We believe OpenSage can pave the way for the next generation of agent development, shifting the focus from human-centered to AI-centered paradigms.
Engineering Systems for Data Analysis Using Interactive Structured Inductive Programming
Dept. of Computer Science \& Information Systems, BITS Pilani, Goa, India School of Computer Science \& Engineering, University of New South Wales, Australia
Agentic AI Software Engineers: Programming with Trust
National University of Singapore(新加坡国立大学);Carnegie Mellon University, KBR Inc., NASA Ames(卡内基梅隆大学、KBR公司、NASA阿姆斯特朗实验室);CISPA Helmholtz Center for Information Security, University of Stuttgart(CISPA海姆霍兹信息安全中心、斯图加特大学);Columbia University(哥伦比亚大学)
Università degli Studi di Genova(热那亚大学);Università degli Studi di Sassari(萨萨里大学);Università della Calabria(卡拉布里亚大学)
答案集编程(ASP)是一种真正的声明式编程范式,在非单调推理和逻辑编程领域提出,最近已在许多应用中使用。因此,开发高效的ASP系统至关重要。考虑到改进ASP的求解方法的任务,有两种常用的方法来实现这一目标:$(i)$扩展最先进的技术和ASP求解器,或$(ii)$从头开始设计一个新的ASP求解器。这些趋势的替代方案是建立在最先进的求解器之上,并应用机器学习技术来自动选择“最好的”可用求解器。在本文中,我们追求这后一个方向。我们首先定义了一组便宜的计算句法功能,表征ASP程序的几个方面。然后,我们应用分类方法,给定{ \sl training}集中的实例的特征和求解器在这些实例上的性能,归纳学习算法选择策略以应用于{ \sl test}集。我们报告了一些实验的结果,考虑到求解器和不同的训练和测试集的情况下,从提交给“系统跟踪”的第三届ASP竞赛。我们的分析表明,通过将机器学习技术应用于ASP求解,可以获得非常稳健的性能:与第三届ASP竞赛的任何求解器相比,我们的方法可以解决更多的实例。(To逻辑程序设计理论与实践(Theory and Practice of Logic Programming,TPLP)