arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.00887cs.CLcs.AIcs.LG
收藏

EffGen: 使小型语言模型成为能干的自主智能体

EffGen: Enabling Small Language Models as Capable Autonomous Agents

Department of Computer Science, Virginia Tech, Blacksburg, VA, USA(弗吉尼亚理工大学计算机科学系);Georgia Institute of Technology, Atlanta, GA, USA(佐治亚理工学院);Google DeepMind, USA(谷歌DeepMind)

Gaurav Srivastava, Aafiya Hussain, Chi Wang, Yingyan Celine Lin, Xuan Wang

AI总结:

EffGen是一个针对小型语言模型优化的开源智能体框架,通过提示压缩、任务分解、复杂度路由和统一记忆系统,实现高效、安全的本地部署,在13个基准测试中优于LangChain等框架。

摘要:

目前大多数基于语言模型的智能体系统都是通过API调用为大型语言模型(如GPT、Claude、Gemini)构建和优化的;虽然强大,但这种方法面临高令牌成本和敏感应用中的隐私问题等限制。我们提出了EffGen,一个针对小型语言模型优化的开源智能体框架,能够实现有效、高效且安全的本地部署。EffGen有四大贡献:(1)增强的工具调用与提示优化,可将输入提示压缩高达70-80%(在我们的基准测试中平均压缩57%),同时保留任务语义;(2)智能任务分解,根据依赖关系将复杂查询分解为并行或顺序子任务;(3)基于复杂度的路由,利用五个因素做出智能的执行前决策;(4)统一记忆系统,结合短期、长期和基于向量的存储。此外,EffGen统一了多种智能体协议(MCP、A2A、ACP)以实现跨协议通信。在13个基准测试上的结果表明,EffGen在成功率、执行速度和内存占用方面优于LangChain、AutoGen和Smolagents。我们的结果揭示,提示优化和复杂度路由具有互补的缩放行为:优化对小型语言模型更有利(1.5B模型提升11.2%,而32B模型提升2.4%),而路由对大型模型更有利(1.5B模型提升3.6%,而32B模型提升7.9%),两者结合在所有规模上都能带来一致的增益。EffGen在Apache 2.0许可证下发布,确保研究和商业用途的广泛可访问性,代码可在https://github.com/effgen/effgen获取,Python包可通过pip install effgen安装,项目网站和文档位于https://effgen.ai和https://docs.effgen.ai。

英文摘要:

Most existing language model agentic systems today are built and optimized for large language models (e.g., GPT, Claude, Gemini) via API calls; while powerful, this approach faces several limitations including high token costs and privacy concerns for sensitive applications. We introduce EffGen, an open-source agentic framework optimized for small language models (SLMs) that enables effective, efficient, and secure local deployment. EffGen makes four major contributions: (1) Enhanced tool-calling with prompt optimization that compresses input prompts by up to 70-80% (and 57% on average across our benchmarks) while preserving task semantics, (2) Intelligent task decomposition that breaks complex queries into parallel or sequential subtasks based on dependencies, (3) Complexity-based routing using five factors to make smart pre-execution decisions, and (4) Unified memory system combining short-term, long-term, and vector-based storage. Additionally, EffGen unifies multiple agent protocols (MCP, A2A, ACP) for cross-protocol communication. Results on 13 benchmarks show EffGen outperforms LangChain, AutoGen, and Smolagents with higher success rates, faster execution, and lower memory. Our results reveal that prompt optimization and complexity routing have complementary scaling behavior: optimization benefits SLMs more (11.2% gain at 1.5B vs 2.4% at 32B), while routing benefits large models more (3.6% at 1.5B vs 7.9% at 32B), providing consistent gains across all scales when combined. EffGen is released under the Apache 2.0 License, ensuring broad accessibility for research and commercial use, with the code available at https://github.com/ctrl-gaurav/effGen, the Python package at https://pypi.org/project/effgen/ (pip install effgen), and the project website and documentation at https://effgen.org/ and https://docs.effgen.org/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑