arXiv cs.MA· Brell Sanwouo, Nada Zine, Paul Temple, Cl\'ement Quinton, Romain Rouvoy·· 12 小时前AI 评分40
GEAR：面向智能体系统的基于特征的配置与代码生成工具
GEAR: Feature-Based Configuration and Code Generation for Agentic Systems
AI 导读
GEAR 是一个开源工具，可从统一规格配置多智能体系统并生成特定框架的实现，通过基于特征的表示让配置选项及其约束显式化，支持在代码生成前校验规格。它提供连接 10 个智能体框架的连接器，初步评估在 320 个特征-框架组合中识别出 271 个的转换策略，占比 84.69%。GEAR 以开源软件形式发布，适用于智能体系统原型开发与跨框架 MAS 配置研究。
正文
Abstract:Engineering multi-agent systems (MAS) requires choosing agents, orchestration strategies, communication mechanisms, reasoning approaches, and memory configurations. These choices depend on framework-specific capabilities and abstractions, requiring developers to learn different APIs when exploring alternative implementations. We present GEAR, an open-source tool for configuring MAS and generating framework-specific implementations from a common specification. GEAR uses a feature-based representation to make configuration options and their constraints explicit, enabling users to validate specifications before code generation. Through connectors for ten agentic frameworks, users generate projects from the same specification and can then inspect reports describing framework-specific adaptations. A preliminary assessment of mapping feasibility identifies translation strategies for 271 of 320 evaluated feature-framework pairs (84.69%). GEAR supports developers prototyping agentic systems and researchers exploring MAS configurations across frameworks. GEAR is available as open-source software at this https URL and a video demo is available at this https URL.
| Subjects: | Multiagent Systems (cs.MA); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.35592 [cs.MA] |
| (or arXiv:2610.35592v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35592 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Brell Sanwouo [view email]
[v1]
Mon, 26 Oct 2026 15:19:22 UTC (702 KB)
来源：arXiv cs.MA · arxiv.org