{"id":30499974,"url":"https://github.com/bytedance-seed/widesearch","last_synced_at":"2025-08-25T07:42:45.876Z","repository":{"id":309340325,"uuid":"1031674752","full_name":"ByteDance-Seed/WideSearch","owner":"ByteDance-Seed","description":"WideSearch: Benchmarking Agentic Broad Info-Seeking","archived":false,"fork":false,"pushed_at":"2025-08-11T09:36:53.000Z","size":479,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-11T11:34:17.621Z","etag":null,"topics":["agent","benchmark","llm"],"latest_commit_sha":null,"homepage":"https://widesearch-seed.github.io/","language":"Python","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/ByteDance-Seed.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}},"created_at":"2025-08-04T06:56:47.000Z","updated_at":"2025-08-11T09:36:56.000Z","dependencies_parsed_at":"2025-08-11T11:34:32.727Z","dependency_job_id":"2fad9d3d-bb34-421a-be95-d572facda74d","html_url":"https://github.com/ByteDance-Seed/WideSearch","commit_stats":null,"previous_names":["bytedance-seed/widesearch"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/ByteDance-Seed/WideSearch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ByteDance-Seed%2FWideSearch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ByteDance-Seed%2FWideSearch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ByteDance-Seed%2FWideSearch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ByteDance-Seed%2FWideSearch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ByteDance-Seed","download_url":"https://codeload.github.com/ByteDance-Seed/WideSearch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ByteDance-Seed%2FWideSearch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272025367,"owners_count":24860531,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-25T02:00:12.092Z","response_time":1107,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["agent","benchmark","llm"],"created_at":"2025-08-25T07:42:41.287Z","updated_at":"2025-08-25T07:42:45.849Z","avatar_url":"https://github.com/ByteDance-Seed.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n\n\u003cdiv align=\"center\"\u003e\n 👋 Hi, everyone! \n    \u003cbr\u003e\n    We are \u003cb\u003eByteDance Seed team.\u003c/b\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  You can get to know us better through the following channels👇\n  \u003cbr\u003e\n  \u003ca href=\"https://seed.bytedance.com/\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Website-%231e37ff?style=for-the-badge\u0026logo=bytedance\u0026logoColor=white\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/user-attachments/assets/5793e67c-79bb-4a59-811a-fcc7ed510bd4\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/WeChat-07C160?style=for-the-badge\u0026logo=wechat\u0026logoColor=white\"\u003e\u003c/a\u003e\n \u003ca href=\"https://www.xiaohongshu.com/user/profile/668e7e15000000000303157d?xsec_token=ABl2-aqekpytY6A8TuxjrwnZskU-6BsMRE_ufQQaSAvjc%3D\u0026xsec_source=pc_search\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Xiaohongshu-%23FF2442?style=for-the-badge\u0026logo=xiaohongshu\u0026logoColor=white\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.zhihu.com/org/dou-bao-da-mo-xing-tuan-dui/\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/zhihu-%230084FF?style=for-the-badge\u0026logo=zhihu\u0026logoColor=white\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n![seed logo](https://github.com/user-attachments/assets/c42e675e-497c-4508-8bb9-093ad4d1f216)\n\n\n# WideSearch: Benchmarking Agentic Broad Info-Seeking\n\u003ca href=\"https://arxiv.org/abs/2508.07999\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/arXiv-b31b1b.svg?style=for-the-badge\u0026logo=arXiv\u0026logoColor=white\"\n         alt=\"arXiv\" /\u003e\n\u003c/a\u003e\n\u003ca href=\"https://widesearch-seed.github.io/\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/Project-Homepage-blue.svg?style=for-the-badge\u0026logo=google-chrome\u0026logoColor=white\"\n         alt=\"Project Homepage\" /\u003e\n\u003c/a\u003e\n\u003ca href=\"https://huggingface.co/datasets/ByteDance-Seed/WideSearch\" target=\"_blank\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Dataset-yellow.svg?style=for-the-badge\"\n         alt=\"Hugging Face Dataset\" /\u003e\n\u003c/a\u003e\n\n---\nWe will release the arxiv paper soon! Stay tuned!\n## News\n[2025/08/11]🔥We release WideSearch Benchmark.\n\n\n## Introduction\n### From Tedious Labor to Autonomous Agent\nMany real-world information-gathering tasks are not hard, just huge. Consider a financial analyst compiling key metrics for all companies in a sector, or a job seeker collecting every vacancy that meets their criteria. The challenge isn't cognitive complexity, but the sheer scale and repetitive nature of the work—a critical productivity bottleneck.\n\nWideSearch is designed to evaluate an agent's ability to automate these tasks, shifting from laborious manual collection to efficient, automated workflows. This shift, however, introduces novel failure modes like hallucination and incompleteness, making rigorous evaluation essential.\n\n\n### A New Paradigm: Wide vs. Deep\nCurrent research primarily focuses on \"deep\" tasks. DeepSearch tackles the \"I can't find it\" problem of locating hidden facts, while DeepResearch addresses the \"I can't write it well\" problem of synthesizing reports.\n\nIn sharp contrast, WideSearch tackles the \"I could do it, but the sheer volume is overwhelming\" problem. It requires agents to systematically find and organize large-scale information into a structured output, shifting the primary challenge from deep search to achieving exhaustiveness and fidelity at scale.\n\n## Experiments\nWe test both single-agent and multi-agent modes, and manually conducted end-to-end testing of the commercial AI system on the web interface. In addition, we randomly select 20 questions and invited human annotators to perform tests. The experiment results are as follows:\n![experiments](figs/image.png)\n\n## Quickstart\n\n## Set up environment\nInstall dependencies, see `prepare-env.sh` for more details.\n```\ngit clone https://github.com/ByteDance-Seed/WideSearch.git\ncd WideSearch\nsh prepare-env.sh\nsource .venv/bin/activate\n```\n\n## Configuration\n1. Implement custom search tools in \u003ca href=\"src/agent/tools.py\"\u003esrc/agent/tools.py\u003c/a\u003e\n2. Configure model parameters in \u003ca href=\"src/utils/config.py\"\u003esrc/utils/config.py\u003c/a\u003e\n\n## Inference and Evaluation\nRun the following command to perform inference and evaluation:\n```\npython3 scripts/run_infer_and_eval_batching.py \\\n--trial_num={your_trial_num} \\\n--model_config_name={your_model_config_name} \\\n--response_root={your_response_root} \\\n--result_save_root={your_result_save_root} \\\n--stage={infer/eval or both} \n``` \n\n## License\nThis project is licensed under MIT. See the \u003ca href=\"LICENSE\"\u003eLICENSE\u003c/a\u003e file for details.\n\n## Citation\nIf you find WideSearch useful for your research and applications, feel free to give us a star ⭐ and cite us using:\n\n```bibtex\n@misc{wong2025widesearchbenchmarkingagenticbroad,\n      title={WideSearch: Benchmarking Agentic Broad Info-Seeking}, \n      author={Ryan Wong and Jiawei Wang and Junjie Zhao and Li Chen and Yan Gao and Long Zhang and Xuan Zhou and Zuo Wang and Kai Xiang and Ge Zhang and Wenhao Huang and Yang Wang and Ke Wang},\n      year={2025},\n      eprint={2508.07999},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL},\n      url={https://arxiv.org/abs/2508.07999}, \n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbytedance-seed%2Fwidesearch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbytedance-seed%2Fwidesearch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbytedance-seed%2Fwidesearch/lists"}