Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and recovering from failures. We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools. Unlike in virtual AI agents, the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning. We refer to this setting as Physical Orchestration, and propose VoLoAgent, a VLM that plans, monitors, and recovers by treating a VLA/WAM as an interruptible tool it steers mid-rollout alongside vision models and action primitives. To evaluate these long-horizon capabilities, we introduce RoboVoLo, a high-fidelity benchmark for open-vocabulary long-horizon manipulation across common sense, memory/state tracking, complex references, and world knowledge, with both task-level success and failure-mode diagnostics. Experiments show VoLoAgent substantially outperforms single VLA/VLM or tool-based systems, with validation on real-robot experiments.</p>\n","updatedAt":"2026-06-10T00:52:39.601Z","author":{"_id":"65f327c5761cd77e9411e303","avatarUrl":"/avatars/2c6c66e54bb2b31923c24929be5e5936.svg","fullname":"Siyi Chen","name":"siyich","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8907249569892883},"editors":["siyich"],"editorAvatarUrls":["/avatars/2c6c66e54bb2b31923c24929be5e5936.svg"],"reactions":[],"isReport":false}},{"id":"6a28c2cda3ce11e99f03df2f","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":363,"isUserFollowing":false},"createdAt":"2026-06-10T01:50:05.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models](https://huggingface.co/papers/2605.13119) (2026)\n* [Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection](https://huggingface.co/papers/2604.13942) (2026)\n* [Long-Horizon Manipulation via Trace-Conditioned VLA Planning](https://huggingface.co/papers/2604.21924) (2026)\n* [RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark](https://huggingface.co/papers/2605.10921) (2026)\n* [LongBench: Evaluating Robotic Manipulation Policies on Real-World Long-Horizon Tasks](https://huggingface.co/papers/2604.16788) (2026)\n* [RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation](https://huggingface.co/papers/2605.17522) (2026)\n* [Long-Term Memory for VLA-based Agents in Open-World Task Execution](https://huggingface.co/papers/2604.15671) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2605.13119\">Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.13942\">Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.21924\">Long-Horizon Manipulation via Trace-Conditioned VLA Planning</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.10921\">RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.16788\">LongBench: Evaluating Robotic Manipulation Policies on Real-World Long-Horizon Tasks</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.17522\">RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.15671\">Long-Term Memory for VLA-based Agents in Open-World Task Execution</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code><span class=\"SVELTE_PARTIAL_HYDRATER contents\" data-target=\"UserMention\" data-props=\"{"user":"librarian-bot"}\"><span class=\"inline-block\"><span class=\"contents\"><a href=\"/librarian-bot\">@<span class=\"underline\">librarian-bot</span></a></span> </span></span> recommend</code></p>\n","updatedAt":"2026-06-10T01:50:05.771Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":363,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7252124547958374},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.07723","authors":[{"_id":"6a28b3f2e7d78ea7587e5246","name":"Siyi Chen","hidden":false},{"_id":"6a28b3f2e7d78ea7587e5247","name":"Hugo Hadfield","hidden":false},{"_id":"6a28b3f2e7d78ea7587e5248","name":"Alex Zook","hidden":false},{"_id":"6a28b3f2e7d78ea7587e5249","name":"Mikaela Angelina Uy","hidden":false},{"_id":"6a28b3f2e7d78ea7587e524a","name":"Chan Hee Song","hidden":false},{"_id":"6a28b3f2e7d78ea7587e524b","name":"Erwin Coumans","hidden":false},{"_id":"6a28b3f2e7d78ea7587e524c","name":"Xuning Yang","hidden":false},{"_id":"6a28b3f2e7d78ea7587e524d","name":"Faisal Ladhak","hidden":false},{"_id":"6a28b3f2e7d78ea7587e524e","name":"Qing Qu","hidden":false},{"_id":"6a28b3f2e7d78ea7587e524f","name":"Stan Birchfield","hidden":false},{"_id":"6a28b3f2e7d78ea7587e5250","name":"Jonathan Tremblay","hidden":false},{"_id":"6a28b3f2e7d78ea7587e5251","name":"Valts Blukis","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/65f327c5761cd77e9411e303/BsNsldGjZM6nK1-YtdbPJ.png"],"publishedAt":"2026-06-05T00:00:00.000Z","submittedOnDailyAt":"2026-06-09T00:00:00.000Z","title":"VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation","submittedOnDailyBy":{"_id":"65f327c5761cd77e9411e303","avatarUrl":"/avatars/2c6c66e54bb2b31923c24929be5e5936.svg","isPro":false,"fullname":"Siyi Chen","user":"siyich","type":"user","name":"siyich"},"summary":"Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and recovering from failures. We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools. Unlike in virtual AI agents, the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning. We refer to this setting as Physical Orchestration, and propose VoLoAgent, a VLM that plans, monitors, and recovers by treating a VLA/WAM as an interruptible tool it steers mid-rollout alongside vision models and action primitives. To evaluate these long-horizon capabilities, we introduce RoboVoLo, a high-fidelity benchmark for open-vocabulary long-horizon manipulation across common sense, memory/state tracking, complex references, and world knowledge, with both task-level success and failure-mode diagnostics. Experiments show VoLoAgent substantially outperforms single VLA/VLM or tool-based systems, with validation on real-robot experiments. Project page: https://chicychen.github.io/VoLo/","upvotes":1,"discussionId":"6a28b3f2e7d78ea7587e5252","projectPage":"https://chicychen.github.io/VoLo/","ai_summary":"VoLoAgent enables physical orchestration by integrating vision-language models with robot capabilities for open-vocabulary long-horizon manipulation tasks.","ai_keywords":["Vision-Language Model","robot capabilities","interruptible tools","long-horizon manipulation","open-vocabulary","physical orchestration","VLA","WAM","task-level success","failure-mode diagnostics"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"60262b67268c201cdc8b7d43","name":"nvidia","fullname":"NVIDIA","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"65f327c5761cd77e9411e303","avatarUrl":"/avatars/2c6c66e54bb2b31923c24929be5e5936.svg","isPro":false,"fullname":"Siyi Chen","user":"siyich","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"60262b67268c201cdc8b7d43","name":"nvidia","fullname":"NVIDIA","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.07723.md"}">
VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation
Authors: ,
,
,
,
,
,
,
,
,
,
,
Abstract
VoLoAgent enables physical orchestration by integrating vision-language models with robot capabilities for open-vocabulary long-horizon manipulation tasks.
Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and recovering from failures. We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools. Unlike in virtual AI agents, the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning. We refer to this setting as Physical Orchestration, and propose VoLoAgent, a VLM that plans, monitors, and recovers by treating a VLA/WAM as an interruptible tool it steers mid-rollout alongside vision models and action primitives. To evaluate these long-horizon capabilities, we introduce RoboVoLo, a high-fidelity benchmark for open-vocabulary long-horizon manipulation across common sense, memory/state tracking, complex references, and world knowledge, with both task-level success and failure-mode diagnostics. Experiments show VoLoAgent substantially outperforms single VLA/VLM or tool-based systems, with validation on real-robot experiments. Project page: https://chicychen.github.io/VoLo/
Community
Open-vocabulary long-horizon manipulation requires robots to reason over flexible instructions and complex multi-object scenes while adaptively planning, executing, monitoring, and recovering from failures. We address these demands with a closed agent loop in which a VLM orchestrates heterogeneous robot capabilities as interruptible tools. Unlike in virtual AI agents, the timing of decisions, actions and tool calls is important in a physical world that does not pause for reasoning. We refer to this setting as Physical Orchestration, and propose VoLoAgent, a VLM that plans, monitors, and recovers by treating a VLA/WAM as an interruptible tool it steers mid-rollout alongside vision models and action primitives. To evaluate these long-horizon capabilities, we introduce RoboVoLo, a high-fidelity benchmark for open-vocabulary long-horizon manipulation across common sense, memory/state tracking, complex references, and world knowledge, with both task-level success and failure-mode diagnostics. Experiments show VoLoAgent substantially outperforms single VLA/VLM or tool-based systems, with validation on real-robot experiments.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.07723 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.07723 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.07723 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.