[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72170":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":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":33,"readmeContent":34,"aiSummary":35,"trendingCount":16,"starSnapshotCount":16,"syncStatus":36,"lastSyncTime":37,"discoverSource":38},72170,"PPTAgent","icip-cas\u002FPPTAgent","icip-cas","An Agentic Framework for Reflective PowerPoint Generation","https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.03936",null,"Python",4627,555,35,5,0,32,107,318,96,30.24,"MIT License",false,"main",[26,27,28,29,30,31,32],"agent","agentic-ai","llm","mcp","openclaw","presentation","slide","2026-06-12 02:02:59","\n\u003Cdiv align=\"right\">\n  \u003Cdetails>\n    \u003Csummary >🌐 Language\u003C\u002Fsummary>\n    \u003Cdiv>\n      \u003Cdiv align=\"center\">\n        \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=en\">English\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=zh-CN\">简体中文\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=zh-TW\">繁體中文\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=ja\">日本語\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=ko\">한국어\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=hi\">हिन्दी\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=th\">ไทย\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=fr\">Français\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=de\">Deutsch\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=es\">Español\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=it\">Italiano\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=ru\">Русский\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=pt\">Português\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=nl\">Nederlands\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=pl\">Polski\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=ar\">العربية\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=fa\">فارسی\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=tr\">Türkçe\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=vi\">Tiếng Việt\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=id\">Bahasa Indonesia\u003C\u002Fa>\n        | \u003Ca href=\"https:\u002F\u002Fopenaitx.github.io\u002Fview.html?user=icip-cas&project=PPTAgent&lang=as\">অসমীয়া\u003C\u002Fa>\n      \u003C\u002Fdiv>\n    \u003C\u002Fdiv>\n  \u003C\u002Fdetails>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"resource\u002Fpptagent-logo.jpg\" width=\"240px\" alt=\"https:\u002F\u002Fgithub.com\u002Ficip-cas\u002FPPTAgent\">\n\u003C\u002Fdiv>\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd width=\"50%\">\n      \u003Cvideo controls width=\"100%\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F314bed6a-185e-4c81-9de5-35728e83e22a\">\n      \u003C\u002Fvideo>\n    \u003C\u002Ftd>\n    \u003Ctd width=\"50%\">\n      \u003Cvideo controls width=\"100%\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F96eee616-5f79-4ea1-bd7f-bcaa466eda9e\">\n      \u003C\u002Fvideo>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\nWe **strongly recommend** deploying our fine-tuned model for the best experience with our agent project. According to our experiments, it **significantly outperforms existing open-source models**.\n\n| Format | HuggingFace | ModelScope |\n|--------|-------------|------------|\n| GGUF (Quantized) | [Forceless\u002FDeepPresenter-9B-GGUF](https:\u002F\u002Fhuggingface.co\u002FForceless\u002FDeepPresenter-9B-GGUF) | [forceless\u002FDeepPresenter-9B-GGUF](https:\u002F\u002Fmodelscope.cn\u002Fmodels\u002Fforceless\u002FDeepPresenter-9B-GGUF) |\n| Full Weights | [Forceless\u002FDeepPresenter-9B](https:\u002F\u002Fhuggingface.co\u002FForceless\u002FDeepPresenter-9B) | [forceless\u002FDeepPresenter-9B](https:\u002F\u002Fmodelscope.cn\u002Fmodels\u002Fforceless\u002FDeepPresenter-9B) |\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"resource\u002Fwechat.jpg\" width=\"140px\">\n\u003C\u002Fdiv>\n\n## 📅 News\n\n- **[2026\u002F04]** 🎉 [DeepPresenter](https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.22839) accepted to **ACL 2026**!\n- **[2026\u002F03]** 🤗 We released fine-tuned models and taskset on [Hugging Face](https:\u002F\u002Fhuggingface.co\u002Fcollections\u002FICIP\u002Fdeeppresenter).\n- **[2026\u002F01]** 🆕 Freeform & template generation now support PPTX export and offline mode. Context management added to prevent context overflow.\n- **[2025\u002F12]** 🔥 Released **DeepPresenter** codebase with major upgrades — Deep Research Integration, Free-Form Visual Design, Autonomous Asset Creation, Text-to-Image Generation, and an Agent Environment with sandbox & 20+ tools.\n- **[2025\u002F09]** 🛠️ MCP server support added — see [MCP Server](PPTAgent\u002FDOC.md#mcp-server-) for configuration details.\n- **[2025\u002F08]** 🎉 [PPTAgent](https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.03936) accepted to **EMNLP 2025**!\n- **[2025\u002F05]** ⭐ Reached **1,000 stars** on GitHub!\n- **[2025\u002F01]** 🔓 Open-sourced the PPTAgent codebase.\n\n## Usage 📖\n\n> [!IMPORTANT]\n> Windows is not supported. If you are on Windows, please use WSL.\n>\n> We strongly recommend starting with the CLI and minimum task to confirm dependencies and environment is configured correctly.\n\n### Configuration\n\nIf you use the CLI, `pptagent onboard` can help create and update these configurations interactively. If you use Docker Compose or build from source, you should prepare them manually:\n\n```bash\ncp deeppresenter\u002Fconfig.yaml.example deeppresenter\u002Fconfig.yaml\ncp deeppresenter\u002Fmcp.json.example deeppresenter\u002Fmcp.json\n```\n\n#### Optional Services That Improve Quality\n\nThe following services can noticeably improve generation quality, especially for research depth, PDF parsing, and visual asset creation:\n\n- **Tavily**: improves web search quality. Apply for an API key at [tavily.com](https:\u002F\u002Fwww.tavily.com\u002F), then set `TAVILY_API_KEY` in [`deeppresenter\u002Fmcp.json`](deeppresenter\u002Fmcp.json).\n- **MinerU**: improves PDF parsing quality. You can either apply for an API key at [mineru.net](https:\u002F\u002Fmineru.net\u002FapiManage\u002Fdocs) and set `MINERU_API_KEY` in [`deeppresenter\u002Fmcp.json`](deeppresenter\u002Fmcp.json), or deploy MinerU locally and set `MINERU_API_URL` instead.\n- **Text-to-image model**: improves image generation quality. Configure `t2i_model` in [`deeppresenter\u002Fconfig.yaml`](deeppresenter\u002Fconfig.yaml).\n\n\nIf you want a fully offline setup, deploy MinerU locally and set `offline_mode: true` in `deeppresenter\u002Fconfig.yaml` to avoid loading network-dependent tools such as web search.\n\nMore configurable variables can be found in [constants.py](deeppresenter\u002Futils\u002Fconstants.py).\n\n### 1. Personal Use \u002F OpenClaw Integration: CLI\n\n> [!NOTE]\n> On macOS, the CLI may automatically install several local dependencies, including Homebrew, Node.js, Docker, poppler, Playwright, and llama.cpp.\n>\n> On Linux, you should prepare the environment by yourself.\n\nUse this mode if you want the fastest local setup or want to plug DeepPresenter into OpenClaw through the CLI.\n\n```bash\n# Install uv\ncurl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n\n# First-time interactive setup\nuvx pptagent onboard\n\n# Generate a presentation\nuvx pptagent generate \"Single Page with Title: Hello World\" -o hello.pptx\n\n# Generate with attachments\nuvx pptagent generate \"Q4 Report\" \\\n  -f data.xlsx \\\n  -f charts.pdf \\\n  -p \"10-12\" \\\n  -o report.pptx\n```\n\n| Command             | Description                                       |\n| ------------------- | ------------------------------------------------- |\n| `pptagent onboard`  | Interactive configuration wizard                  |\n| `pptagent generate` | Generate presentations                            |\n| `pptagent config`   | View current configuration                        |\n| `pptagent reset`    | Reset configuration                               |\n| `pptagent serve`    | Start the local inference service used by the CLI |\n\n### 2. Minimal Setup \u002F Development: Build From Source\n\nUse this mode if you want the smallest abstraction layer and full control over dependencies during development.\n\n```bash\nuv pip install -e .\nplaywright install-deps\nplaywright install chromium\nnpm install --prefix deeppresenter\u002Fhtml2pptx\nmodelscope download forceless\u002Ffasttext-language-id\n\ndocker pull forceless\u002Fdeeppresenter-sandbox\ndocker pull forceless\u002Fdeeppresenter-host\ndocker tag forceless\u002Fdeeppresenter-sandbox deeppresenter-sandbox\n\n# or build from dockerfile\ndocker build -t deeppresenter-sandbox -f deeppresenter\u002Fdocker\u002FSandBox.Dockerfile .\n```\n\nStart the app:\n\n```bash\npython webui.py\n```\n\n### 3. Server Deployment: Docker Compose\n\nUse this mode for a stable server environment with explicit dependencies.\n\n```bash\n# Pull the public images to avoid build from source\ndocker pull forceless\u002Fdeeppresenter-sandbox\ndocker tag forceless\u002Fdeeppresenter-sandbox deeppresenter-sandbox\n\n# Or build from source\ndocker build -t deeppresenter-sandbox -f deeppresenter\u002Fdocker\u002FSandBox.Dockerfile .\n\n# Start the host service\ndocker compose up -d\n```\n\nThe service exposes the web UI on `http:\u002F\u002Flocalhost:7861`.\n\n## Case Study 💡\n\n- #### Prompt: Please present the given document to me.\n\n\u003Cdiv style=\"display: flex; flex-wrap: wrap; gap: 10px;\">\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0001.jpg\" alt=\"图片1\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0002.jpg\" alt=\"图片2\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0003.jpg\" alt=\"图片3\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0004.jpg\" alt=\"图片4\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0005.jpg\" alt=\"图片5\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0006.jpg\" alt=\"图片6\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0007.jpg\" alt=\"图片7\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0008.jpg\" alt=\"图片8\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0009.jpg\" alt=\"图片9\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fmanuscript\u002F0010.jpg\" alt=\"图片10\" width=\"200\"\u002F>\n\n\u003C\u002Fdiv>\n\n- #### Prompt: 请介绍小米 SU7 的外观和价格\n\n\u003Cdiv style=\"display: flex; flex-wrap: wrap; gap: 10px;\">\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation1\u002F0001.jpg\" alt=\"图片1\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation1\u002F0002.jpg\" alt=\"图片2\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation1\u002F0003.jpg\" alt=\"图片3\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation1\u002F0004.jpg\" alt=\"图片4\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation1\u002F0005.jpg\" alt=\"图片5\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation1\u002F0006.jpg\" alt=\"图片6\" width=\"200\"\u002F>\n\n\u003C\u002Fdiv>\n\n- #### Prompt: 请制作一份高中课堂展示课件，主题为“解码立法过程：理解其对国际关系的影响”\n\n\u003Cdiv style=\"display: flex; flex-wrap: wrap; gap: 10px;\">\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0001.jpg\" alt=\"图片1\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0002.jpg\" alt=\"图片2\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0003.jpg\" alt=\"图片3\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0004.jpg\" alt=\"图片4\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0005.jpg\" alt=\"图片5\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0006.jpg\" alt=\"图片6\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0007.jpg\" alt=\"图片7\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0008.jpg\" alt=\"图片8\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0009.jpg\" alt=\"图片9\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0010.jpg\" alt=\"图片10\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0011.jpg\" alt=\"图片11\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0012.jpg\" alt=\"图片12\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0013.jpg\" alt=\"图片13\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0014.jpg\" alt=\"图片14\" width=\"200\"\u002F>\n\n  \u003Cimg src=\"resource\u002Fv2\u002Fpresentation2\u002F0015.jpg\" alt=\"图片15\" width=\"200\"\u002F>\n\n\u003C\u002Fdiv>\n\n---\n\n## Contributors 🌟\n\n\u003Ctable>\n\u003Ctr>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FForce1ess>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72636351?v=4 width=\"80;\"  alt=Force1ess\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Force1ess\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FPuellaquae>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F22560343?v=4 width=\"80;\"  alt=Puelloc\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Puelloc\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002Fhysyyds>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F80150669?v=4 width=\"80;\"  alt=hongyan\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>hongyan\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FimHuZijian>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F97173940?v=4 width=\"80;\"  alt=BrandonHu\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>BrandonHu\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FDnoob>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92987618?v=4 width=\"80;\"  alt=Dnoob\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Dnoob\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FSadahlu>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F126563707?v=4 width=\"80;\"  alt=Sadahlu\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Sadahlu\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FKurisuMakiseSame>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F168447425?v=4 width=\"80;\"  alt=KurisuMakiseSame\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>KurisuMakiseSame\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FRheagalFire>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F60213893?v=4 width=\"80;\"  alt=Aarish Alam\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Aarish Alam\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FAngelenx>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39873863?v=4 width=\"80;\"  alt=Angelen\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Angelen\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002Fkylooh>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26456650?v=4 width=\"80;\"  alt=Eliot White\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Eliot White\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FEvolvedGhost>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92856393?v=4 width=\"80;\"  alt=EvolvedGhost\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>EvolvedGhost\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FISCAS-zwl>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F179820048?v=4 width=\"80;\"  alt=ISCAS-zwl\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>ISCAS-zwl\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FJames4Ever0>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F103997068?v=4 width=\"80;\"  alt=James Brown\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>James Brown\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FLasRuinasCirculares>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F119716645?v=4 width=\"80;\"  alt=JunZhang\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>JunZhang\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002Fopenaitx-system>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F215529505?v=4 width=\"80;\"  alt=Open AI Tx\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Open AI Tx\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002Fhaosenwang1018>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F167664334?v=4 width=\"80;\"  alt=Sense_wang\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Sense_wang\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FDeJeune>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F67425183?v=4 width=\"80;\"  alt=SuYao\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>SuYao\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FJiwaniZakir>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108548454?v=4 width=\"80;\"  alt=Zakir Jiwani\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Zakir Jiwani\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002FDormiveglia-elf>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F81767213?v=4 width=\"80;\"  alt=Zhenyu\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>Zhenyu\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd align=\"center\" style=\"word-wrap: break-word; width: 120.0; height: 120.0\">\n        \u003Ca href=https:\u002F\u002Fgithub.com\u002Flnennnn>\n            \u003Cimg src=https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F124434018?v=4 width=\"80;\"  alt=lnennnn\u002F>\n            \u003Cbr \u002F>\n            \u003Csub style=\"font-size:14px\">\u003Cb>lnennnn\u003C\u002Fb>\u003C\u002Fsub>\n        \u003C\u002Fa>\n    \u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=icip-cas\u002FPPTAgent&type=Date)](https:\u002F\u002Fstar-history.com\u002F#icip-cas\u002FPPTAgent&Date)\n\n## Citation 🙏\n\nIf you find this project helpful, please use the following to cite it:\n```bibtex\n@inproceedings{zheng-etal-2025-pptagent,\n    title = \"{PPTA}gent: Generating and Evaluating Presentations Beyond Text-to-Slides\",\n    author = \"Zheng, Hao  and\n      Guan, Xinyan  and\n      Kong, Hao  and\n      Zhang, Wenkai  and\n      Zheng, Jia  and\n      Zhou, Weixiang  and\n      Lin, Hongyu  and\n      Lu, Yaojie  and\n      Han, Xianpei  and\n      Sun, Le\",\n    editor = \"Christodoulopoulos, Christos  and\n      Chakraborty, Tanmoy  and\n      Rose, Carolyn  and\n      Peng, Violet\",\n    booktitle = \"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2025\",\n    address = \"Suzhou, China\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https:\u002F\u002Faclanthology.org\u002F2025.emnlp-main.728\u002F\",\n    doi = \"10.18653\u002Fv1\u002F2025.emnlp-main.728\",\n    pages = \"14413--14429\",\n    ISBN = \"979-8-89176-332-6\",\n    abstract = \"Automatically generating presentations from documents is a challenging task that requires accommodating content quality, visual appeal, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, overlooking visual appeal and structural coherence, which limits their practical applicability. To address these limitations, we propose PPTAgent, which comprehensively improves presentation generation through a two-stage, edit-based approach inspired by human workflows. PPTAgent first analyzes reference presentations to extract slide-level functional types and content schemas, then drafts an outline and iteratively generates editing actions based on selected reference slides to create new slides. To comprehensively evaluate the quality of generated presentations, we further introduce PPTEval, an evaluation framework that assesses presentations across three dimensions: Content, Design, and Coherence. Results demonstrate that PPTAgent significantly outperforms existing automatic presentation generation methods across all three dimensions.\"\n}\n\n@misc{zheng2026deeppresenterenvironmentgroundedreflectionagentic,\n      title={DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation},\n      author={Hao Zheng and Guozhao Mo and Xinru Yan and Qianhao Yuan and Wenkai Zhang and Xuanang Chen and Yaojie Lu and Hongyu Lin and Xianpei Han and Le Sun},\n      year={2026},\n      eprint={2602.22839},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https:\u002F\u002Farxiv.org\u002Fabs\u002F2602.22839},\n}\n```\n","PPTAgent 是一个用于生成反思性 PowerPoint 演示文稿的代理框架。该项目利用了大型语言模型（LLM）和多模态内容规划（MCP）技术，能够自动生成结构合理、内容丰富的演示文稿。它支持从文本到幻灯片的自动转换，并且可以根据用户提供的主题或关键词生成相应的演示材料。PPTAgent 适合需要快速创建专业演示文稿的场景，如学术报告、企业展示以及教育培训等场合。项目采用 Python 编写，遵循 MIT 许可证，社区活跃度高，拥有超过4300个星标。",2,"2026-06-11 03:40:40","high_star"]