{"id":41947829,"url":"https://github.com/baidubce/FM-Agent","last_synced_at":"2026-02-04T17:01:30.895Z","repository":{"id":321398434,"uuid":"1085688085","full_name":"baidubce/FM-Agent","owner":"baidubce","description":null,"archived":false,"fork":false,"pushed_at":"2025-11-23T14:41:42.000Z","size":31134,"stargazers_count":52,"open_issues_count":2,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-11-23T15:20:42.369Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/baidubce.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-29T11:33:03.000Z","updated_at":"2025-11-23T14:41:46.000Z","dependencies_parsed_at":"2025-10-29T13:28:18.142Z","dependency_job_id":null,"html_url":"https://github.com/baidubce/FM-Agent","commit_stats":null,"previous_names":["baidubce/fm-agent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/baidubce/FM-Agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baidubce%2FFM-Agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baidubce%2FFM-Agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baidubce%2FFM-Agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baidubce%2FFM-Agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/baidubce","download_url":"https://codeload.github.com/baidubce/FM-Agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baidubce%2FFM-Agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29091317,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-04T03:31:03.593Z","status":"ssl_error","status_checked_at":"2026-02-04T03:29:50.742Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-01-25T20:00:26.085Z","updated_at":"2026-02-04T17:01:30.890Z","avatar_url":"https://github.com/baidubce.png","language":null,"funding_links":[],"categories":["AutoML Agents"],"sub_categories":[],"readme":"\u003cdiv align=\"right\"\u003e\n  \u003ca href=\"README_CN.md\"\u003e简体中文\u003c/a\u003e | \u003cb\u003eEnglish\u003c/b\u003e\n\u003c/div\u003e\n\n\u003ch1 align=\"center\"\u003eFaMou Agent\u003c/h1\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n🚩 \u003ca href=\"https://cloud.baidu.com/product/famou.html\" style=\"vertical-align:middle;\"\u003e **Official Website**\u003c/a\u003e |\n📄 **[Tech Report](https://github.com/baidubce/FM-Agent/blob/main/docs/FMAgent_TechReport.pdf)** |\n📌  \u003ca href=\"https://arxiv.org/pdf/2510.26144\" style=\"vertical-align:middle;\"\u003e **Arxiv Link**\u003c/a\u003e |\n\u003ca href=\"https://cloud.baidu.com/\" style=\"vertical-align:middle;\"\u003e\u003cimg src=\"docs/images/ACG.png\" alt=\"ModelBuilder\" width=\"16\" height=\"16\" style=\"vertical-align:middle;\"/\u003e **Baidu AI Cloud**\u003c/a\u003e\n\u003c/div\u003e\n\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/main.png\" width=\"700\" height=\"700\"/\u003e\n\u003c/p\u003e\n \n## Introduction\nFM Agent is a novel, general-purpose multi-agent framework that addresses complex real-world challenges by synergistically combining LLM-based reasoning and large-scale evolutionary search. Demonstrating broad applicability, our system has been evaluated across diverse domains, including operations research, machine learning, GPU kernel optimization, and classical mathematical problems.\n\n\n## Technical Advantages\n### ❄️ Cold-Start Initialization\nThis phase integrates  diverse generation agents to produce a broad yet high-quality initial solution space. Moreover, with an optional expert-in-the-loop design, the framework ensures evolutionary search begins from a pragmatically grounded foundation, significantly accelerating convergence, especially in some real-world complex cases.\n\n### 🧬 Adaptive Diversity-Driven Sampling\nOur novel sampling strategy orchestrates multiple parallel evolutionary islands, adaptively balancing exploration and exploitation through dynamic resource allocation. This mechanism maintains productive diversity across algorithmic lineages while systematically steering the population toward global optima.\n\n### 🎯 Domain-Specific Evaluation\nCustom evaluators synthesize multiple critical criteria—including functional correctness, operational effectiveness, and LLM-supervised quality assessment—to generate nuanced, multi-faceted feedback. This comprehensive scoring mechanism provides rich, cumulative signals that precisely guide the iterative refinement process.\n\n### 🚀 Distributed Asynchronous Infrastructure\nBuilt on Ray, our scalable orchestration framework enables fine-grained, large-scale concurrent evaluation across distributed computing resources. This architecture ensures efficient resource utilization while facilitating rapid and systematic exploration of complex, high-dimensional solution spaces.\n  \n## Performance Metrics\nFM Agent reaches state-of-the-art results autonomously, without human interpretation or tuning — **1976.3** on ALE-Bench (+5.2%), **43.56**% on MLE-bench (+4.0pp), up to **20×** speedups on KernelBench, and establishes new state-of-the-art(SOTA) results on several classical mathematical problems.\n\n### MLE-bench\n💥💥💥FM Agent is currently ranked first on the [MLE-bench Leaderboard](https://github.com/openai/mle-bench?tab=readme-ov-file).\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/mlebench_result.png\" width=\"500\" height=\"500\"/\u003e\n\u003c/p\u003e\n\n\n### ALE-Bench\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/alebench_result.png\" width=\"500\" height=\"500\"/\u003e\n\u003c/p\u003e\n\n\n### KernelBench\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/kernelbench_result.png\" width=\"500\" height=\"500\"/\u003e\n\u003c/p\u003e\n\n## Citation\n\nIf you use FM Agent in your research, please cite:\n\n```bibtex\n@misc{li2025fmagent,\n      title={The FM Agent}, \n      author={Annan Li and Chufan Wu and Zengle Ge and Yee Hin Chong and Zhinan Hou and Lizhe Cao and Cheng Ju and Jianmin Wu and Huaiming Li and Haobo Zhang and Shenghao Feng and Mo Zhao and Fengzhi Qiu and Rui Yang and Mengmeng Zhang and Wenyi Zhu and Yingying Sun and Quan Sun and Shunhao Yan and Danyu Liu and Dawei Yin and Dou Shen},\n      year={2025},\n      eprint={2510.26144},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https://arxiv.org/abs/2510.26144}, \n}\n```\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n\n## Contact Us\n\n- GitHub Issues: [Submit Issue](https://github.com/baidubce/FM-Agent/issues)\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbaidubce%2FFM-Agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbaidubce%2FFM-Agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbaidubce%2FFM-Agent/lists"}