[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71135":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":23,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":28,"readmeContent":29,"aiSummary":30,"trendingCount":16,"starSnapshotCount":16,"syncStatus":31,"lastSyncTime":32,"discoverSource":33},71135,"agents","aiwaves-cn\u002Fagents","aiwaves-cn","An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents","",null,"Python",5930,480,60,40,0,1,9,65.45,"Apache License 2.0",false,"master",true,[25,26,27],"autonomous-agents","language-model","llm","2026-06-12 04:00:59","\u003Cdiv align=\"center\">\n\u003Cimg src='.\u002Fassets\u002Fagents-logo.png'  width=300px>\n\n## \u003Cp align=\"center\">Agents 2.0: Symbolic Learning Enables Self-Evolving Agents\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n\u003Ca href=\"https:\u002F\u002Faiwaves-cn.github.io\u002Fagents\u002F\">[🤖Project]\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.18532\">[📄Paper]\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fagentsv2.readthedocs.io\u002F\">[📝Docs]\u003C\u002Fa>\n\u003Ca href=\"#overview\">[🌟Overview]\u003C\u002Fa>\n\u003Ca href=\"#installation\">[🔧Installation]\u003C\u002Fa>\n\u003Ca href=\"#citation\">[🚩Citation]\u003C\u002Fa>\n\u003C\u002Fp>\n\n![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fversion-v2.0.0-blue)\n[![License: Apache](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache2.0-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicense\u002Fapache-2-0)\n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Faiwaves-cn\u002Fagents?color=green)\n![](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-Welcome-red) \n\n---\n\n\u003C\u002Fdiv>\n\n\n## 🔔News\n- [2024-06-25] We release [Agents](https:\u002F\u002Fagentsv2.readthedocs.io\u002Fen\u002Flatest\u002F) 2.0, a major update to the original library, adding support for agent learning and evaluation.\n---\n\n## 🌟Overview\n\nAgent symbolic learning is a systematic framework for training language agents, which is inspired by the connectionist learning procedure used for training neural nets. We make an analogy between language agents and neural nets: the agent pipeline of an agent corresponds to the computational graph of a neural net, a node in the agent pipeline corresponds to a layer in the neural net, and the prompts and tools for a node correspond to the weights of a layer. In this way, we are able to implement the main components of connectionist learning, i.e., backward propagation and gradient-based weight update, in the context of agent training using language-based loss, gradients, and weights.\n\n\u003Cimg src='.\u002Fassets\u002Foverview.png'>\n\nWe implement loss function, back-propagation, and weight optimizer in the context of agent training with carefully designed prompt pipelines. For a training example, our framework first conducts the \"forward pass\" (agent execution) and stores the input, output, prompts, and tool usage in each node in a \"trajectory\". We then use a prompt-based loss function to evaluate the outcome, resulting in a \"language loss\". Afterward, we back-propagate the language loss from the last to the first node along the trajectory, resulting in textual analyses and reflections for the symbolic components within each node, we call them language gradients. Finally, we update all symbolic components in each node, as well as the computational graph consisting of the nodes and their connections, according to the language gradients with another carefully designed prompt. Our approach also naturally supports optimizing multi-agent systems by considering nodes as different agents or allowing multiple agents to take actions in one node. \n\n### Workflow Illustration\n\n\u003Cimg src='.\u002Fassets\u002Fworkflow.gif'>\n\n---\n\n\n## 🔧Installation\n\n**Installation from git repo branch:**\n```\npip install git+https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002Fagents@master\n```\n\n**Installation for local development:**\n```\ngit clone -b master https:\u002F\u002Fgithub.com\u002Faiwaves-cn\u002Fagents\ncd agents\npip install -e .\n```\n\n---\n\n## ⭐ Star History  \n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=aiwaves-cn\u002Fagents&type=Date)](https:\u002F\u002Fstar-history.com\u002F#aiwaves-cn\u002Fagents&Date)\n\n---\n\n## 🚩Citation\n\nIf you find our repository useful in your research, please kindly consider cite:\n```bibtex\n@article{zhou2024agents2,\n      title={Symbolic Learning Enables Self-Evolving Agents}, \n      author={Wangchunshu Zhou and Yixin Ou and Shengwei Ding and Long Li and Jialong Wu and Tiannan Wang and Jiamin Chen and Shuai Wang and Xiaohua Xu and Ningyu Zhang and Huajun Chen and Yuchen Eleanor Jiang},\n      year={2024},\n      eprint={2406.18532},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https:\u002F\u002Farxiv.org\u002Fabs\u002F2406.18532}, \n}\n\n@article{zhou2023agents,\n      title={Agents: An Open-source Framework for Autonomous Language Agents}, \n      author={Wangchunshu Zhou and Yuchen Eleanor Jiang and Long Li and Jialong Wu and Tiannan Wang and Shi Qiu and Jintian Zhang and Jing Chen and Ruipu Wu and Shuai Wang and Shiding Zhu and Jiyu Chen and Wentao Zhang and Xiangru Tang and Ningyu Zhang and Huajun Chen and Peng Cui and Mrinmaya Sachan},\n      year={2023},\n      eprint={2309.07870},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.07870}, \n}\n```\n","aiwaves-cn\u002Fagents 是一个面向数据、能够自我进化的自主语言代理开源框架。该项目采用Python开发，通过符号学习方法实现类似于神经网络的训练流程，包括前向传递、损失计算、反向传播和基于梯度的权重更新，但这些过程都是在自然语言处理的背景下完成的。它支持单个或多个代理的学习与优化，并且可以调整代理内部结构及其连接方式以适应不同的任务需求。适用于需要构建能够根据环境反馈自动调整策略的语言模型的应用场景，如智能对话系统、自动化内容生成等。",2,"2026-06-11 03:36:03","high_star"]