paper-with-me

홈 › Papers

OpenSage: Self-programming Agent Generation Engine

2026-02-18 · Hongwei Li, Zhun Wang, Qinrun Dai, Yuzhou Nie, Jinjun Peng, Ruitong Liu, Jingyang Zhang, Kaijie Zhu, Jingxuan He, Lun Wang, Yangruibo Ding, Yueqi Chen, Wenbo Guo, Dawn Song arxiv

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.

📄 PDF Abstract BibTeX arXiv:2602.16891

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Loosely-Structured Software: Engineering Context, Structure, and Evolution Entropy in Runtime-Rewired Multi-Agent Systems

2026-03-16 · Weihao Zhang, Yitong Zhou, Huanyu Qu, Hongyi Li arxiv

As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination erro…

VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?

2026-03-16 · Srijan Bansal, Jiao Fangkai, Yilun Zhou, Austin Xu 외 arxiv

As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle faults -- a capability central to autonomo…

Program Repair

The Ann Arbor Architecture for Agent-Oriented Programming

2025-02-14 · Wei Dong

In this paper, we reexamine prompt engineering for large language models through the lens of automata theory. We argue that language models function as automata and, like all automata, should be programmed in the languag…

In-Context LearningPrompt Engineering

OmniCode: A Benchmark for Evaluating Software Engineering Agents

2026-02-02 · Atharv Sonwane, Eng-Shen Tu, Wei-Chung Lu, Claas Beger 외 arxiv

LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require challenging benchmarks that can rigorously evaluate the ability of such agents…

Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models

2026-04-23 · Chee Wei Tan, Yuchen Wang, Shangxin Guo arxiv

This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxonomy of game-playing machines. Central to this paradigm is Nemobot, …

Reinforcement LearningMathematical Reasoning