OpenSage: Self-programming Agent Generation Engine
- URL: http://arxiv.org/abs/2602.16891v1
- Date: Wed, 18 Feb 2026 21:16:29 GMT
- Title: OpenSage: Self-programming Agent Generation Engine
- Authors: 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,
- Abstract summary: We propose OpenSage, the first agent development kit (ADK) to automatically create agents with self-generated topology and toolsets.<n>OpenSage offers effective functionality for agents to create and manage their own sub-agents and toolkits.<n>We believe OpenSage can pave the way for the next generation of agent development, shifting the focus from human-centered to AI-centered paradigms.
- Score: 56.399761469404496
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- A Lightweight Modular Framework for Constructing Autonomous Agents Driven by Large Language Models: Design, Implementation, and Applications in AgentForge [1.932555230783329]
Lightweight, open-source Python framework designed to democratize the construction of LLM-driven autonomous agents.<n>AgentForge introduces three key innovations: (1) a composable skill abstraction that enables fine-grained task decomposition with formally defined input-output contracts, (2) a unified backend interface supporting seamless switching between cloud-based APIs and local inference engines, and (3) a declarative YAML-based configuration system that separates agent logic from implementation details.
arXiv Detail & Related papers (2026-01-19T20:33:26Z) - Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases [44.366968508477235]
We introduce the Confucius Code Agent (CCA), a scalable software engineering agent that can operate at large-scales.<n>CCA is built on top of the Confucius SDK, an agent development platform structured around three complementary perspectives.<n>In addition, we introduce a meta-agent that automates the synthesis, evaluation, and refinement of agent configurations.
arXiv Detail & Related papers (2025-12-11T08:05:58Z) - The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents [46.254487394746725]
We present the OpenHands Software Agent SDK, a toolkit for implementing software development agents.<n>To achieve flexibility, we design a simple interface for implementing agents that requires only a few lines of code in the default case.<n>For security and reliability, it delivers seamless local-to-remote execution portability, integrated REST/WebSocket services.
arXiv Detail & Related papers (2025-11-05T18:16:44Z) - ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools [4.751741320941162]
ToolBrain is a framework for coaching tool use in agentic models with flexible reinforcement learning (RL)<n>It supports a wide range of training strategies, including RL algorithms such as GRPO and DPO, as well as supervised learning.<n>It is packed with useful capabilities, including knowledge distillation from large to small models for efficient development, automatic task generation from tool descriptions, seamless tool retrieval, efficient fine-tuning pipelines with QLoRA through Unsloth, and quantized inference via bitsandbytes.
arXiv Detail & Related papers (2025-09-24T16:01:05Z) - AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications [95.42093979627703]
AgentScope supports flexible and efficient tool-based agent-environment interactions.<n>We ground agent behaviors in the ReAct paradigm and offer advanced agent-level infrastructure.<n>AgentScope also includes robust engineering support for developer-friendly experiences.
arXiv Detail & Related papers (2025-08-22T10:35:56Z) - OpenCUA: Open Foundations for Computer-Use Agents [74.61449905487565]
Vision-language models have demonstrated impressive capabilities as computer-use agents (CUAs)<n>We propose OpenCUA, a comprehensive open-source framework for scaling CUA data and foundation models.<n>Our end-to-end agent models demonstrate strong performance across CUA benchmarks.
arXiv Detail & Related papers (2025-08-12T17:52:32Z) - AgentFly: Extensible and Scalable Reinforcement Learning for LM Agents [25.735754822676277]
Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks.<n> reinforcement learning (RL) has been explored to enhance LM's capabilities, such as reasoning and factuality.<n>We built AgentFly, a scalable and Agent-RL framework designed to empower LM agents with a variety of RL algorithms.
arXiv Detail & Related papers (2025-07-20T10:22:36Z) - SMART: Self-Aware Agent for Tool Overuse Mitigation [58.748554080273585]
Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness.<n>This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks with parametric knowledge.<n>We introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse.
arXiv Detail & Related papers (2025-02-17T04:50:37Z) - SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [79.07755560048388]
SWE-agent is a system that facilitates LM agents to autonomously use computers to solve software engineering tasks.
SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs.
We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively.
arXiv Detail & Related papers (2024-05-06T17:41:33Z) - AgentScope: A Flexible yet Robust Multi-Agent Platform [66.64116117163755]
AgentScope is a developer-centric multi-agent platform with message exchange as its core communication mechanism.
The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment.
arXiv Detail & Related papers (2024-02-21T04:11:28Z)
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.