This survey reframes modern robot learning around <strong>what actually ships—frozen policy weights versus executable skills—and introduces a five-rung taxonomy of code-as-policy systems based on increasingly powerful combinations of execution feedback, persistent memory, and program search, culminating in autonomous self-improving robot skill loops.</strong> </p>\n<p>➡️ 𝐊𝐞𝐲 𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬 𝐨𝐟 𝐭𝐡𝐞 𝐖𝐞𝐢𝐠𝐡𝐭𝐬-𝐯𝐬-𝐒𝐤𝐢𝐥𝐥𝐬 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤:</p>\n<p>🧭 𝑾𝒆𝒊𝒈𝒉𝒕𝒔 𝒗𝒔. 𝑺𝒌𝒊𝒍𝒍𝒔 𝑻𝒂𝒙𝒐𝒏𝒐𝒎𝒚: Introduces a unified taxonomy spanning <strong>77 core systems across six robot-learning families</strong>—code-as-policy, end-to-end VLA, reward synthesis, skill libraries, sim-to-real/transfer, and benchmarks—plus 225 landscape works. Its key architectural distinction is whether competence is encoded in <strong>frozen neural weights</strong> (e.g., VLA backbone + action head) or represented as <strong>inspectable, executable programs/skills</strong> that can be edited and recombined after deployment. The taxonomy on page 3 makes this decomposition explicit. </p>\n<p>🔄 𝑭𝒊𝒗𝒆-𝑹𝒖𝒏𝒈 𝑺𝒆𝒍𝒇-𝑰𝒎𝒑𝒓𝒐𝒗𝒆𝒎𝒆𝒏𝒕 𝑳𝒂𝒅𝒅𝒆𝒓 (𝑭 + 𝑴 + 𝑺): The paper's main analytical novelty is decomposing code-as-policy agents by three operational mechanisms—<strong>Feedback (F)</strong> from execution, <strong>Memory (M)</strong> persisted across tasks, and <strong>Search (S)</strong> over multiple candidate programs—and arranging systems from <strong>zero-shot synthesis → closed-loop repair → skill-library accumulation → evolutionary search → full F+M+S self-improvement</strong>. Crucially, it distinguishes sequential debugging from genuine search and frozen model parameters from runtime memory, making “self-improvement” technically testable rather than a loose label. </p>\n<p>🧠 𝑭𝒖𝒍𝒍 𝑺𝒆𝒍𝒇-𝑰𝒎𝒑𝒓𝒐𝒗𝒊𝒏𝒈 𝑹𝒐𝒃𝒐𝒕 𝑳𝒐𝒐𝒑 + 𝑺𝒌𝒊𝒍𝒍 𝑬𝒄𝒐𝒏𝒐𝒎𝒚: Identifies a sparsely populated frontier—represented by <strong>ASPIRE, ENPIRE, and RoboClaw</strong>—where an agent executes skills, obtains grounded traces/feedback, stores validated skills in persistent memory, and searches/mutates candidate programs, feeding accumulated competence into future tasks. The architecture is summarized in the <strong>page-11 diagram as Actor Agent → Execution Engine (F) → Skill Memory (M) → Evolutionary Search (S)</strong> with skills recursively returned to future tasks. The survey argues this is the missing adaptation layer between today's static robot-skill marketplaces and genuinely deployable, continually improving robot ecosystems.</p>\n","updatedAt":"2026-08-07T21:49:16.372Z","author":{"_id":"63a4754927f1f64ed7238dac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63a4754927f1f64ed7238dac/aH-eJF-31g4vof9jv2gmI.jpeg","fullname":"Aman Chadha","name":"amanchadha","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":9,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8180489540100098},"editors":["amanchadha"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/63a4754927f1f64ed7238dac/aH-eJF-31g4vof9jv2gmI.jpeg"],"reactions":[],"isReport":false}},{"id":"6a768792be02c2153fb53932","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":378,"isUserFollowing":false},"createdAt":"2026-08-08T01:34:10.000Z","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* [ASPIRE: Agentic /Skills Discovery for Robotics](https://huggingface.co/papers/2607.00272) (2026)\n* [A Few Words Go a Long Way: Language Guided Robot Policy Synthesis](https://huggingface.co/papers/2607.23784) (2026)\n* [RHO: Your Coding Agent is Secretly a Roboticist](https://huggingface.co/papers/2606.16458) (2026)\n* [Sequential Planning via Anchored Robotic Keypoints](https://huggingface.co/papers/2606.30613) (2026)\n* [SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation](https://huggingface.co/papers/2607.08354) (2026)\n* [LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories](https://huggingface.co/papers/2606.13578) (2026)\n* [ETA: A New Agentic Paradigm for Embodied Tasks](https://huggingface.co/papers/2608.03924) (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/2607.00272\">ASPIRE: Agentic /Skills Discovery for Robotics</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2607.23784\">A Few Words Go a Long Way: Language Guided Robot Policy Synthesis</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.16458\">RHO: Your Coding Agent is Secretly a Roboticist</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.30613\">Sequential Planning via Anchored Robotic Keypoints</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2607.08354\">SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2606.13578\">LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2608.03924\">ETA: A New Agentic Paradigm for Embodied Tasks</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>@librarian-bot recommend</code></p>\n","updatedAt":"2026-08-08T01:34:10.072Z","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":378,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7353813648223877},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.01851","authors":[{"_id":"6a76484a8e9301703eaa58ad","name":"Gaytri Jena","hidden":false},{"_id":"6a76484a8e9301703eaa58ae","name":"Kapil Wanaskar","hidden":false},{"_id":"6a76484a8e9301703eaa58af","name":"Vinija Jain","hidden":false},{"_id":"6a76484a8e9301703eaa58b0","user":{"_id":"63a4754927f1f64ed7238dac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63a4754927f1f64ed7238dac/aH-eJF-31g4vof9jv2gmI.jpeg","isPro":false,"fullname":"Aman Chadha","user":"amanchadha","type":"user","name":"amanchadha"},"name":"Aman Chadha","status":"claimed_verified","statusLastChangedAt":"2026-08-08T00:45:04.562Z","hidden":false},{"_id":"6a76484a8e9301703eaa58b1","name":"Vasu Sharma","hidden":false},{"_id":"6a76484a8e9301703eaa58b2","name":"Amitava Das","hidden":false}],"publishedAt":"2026-08-03T00:00:00.000Z","submittedOnDailyAt":"2026-08-07T00:00:00.000Z","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","submittedOnDailyBy":{"_id":"63a4754927f1f64ed7238dac","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63a4754927f1f64ed7238dac/aH-eJF-31g4vof9jv2gmI.jpeg","isPro":false,"fullname":"Aman Chadha","user":"amanchadha","type":"user","name":"amanchadha"},"summary":"Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that write and refine their own executable skills as code. This survey organises the field around that axis of weights versus skills. Its central analytical contribution is a deep-dive that arranges code-as-policy methods by their degree of self-improvement, from zero-shot program synthesis, through closed-loop self-repair and persistent skill memory, to the sparsely populated cell in which execution feedback, skill memory, and evolutionary search combine into one open-ended loop; only a few very recent systems (for example ASPIRE, ENPIRE, and RoboClaw) occupy that cell. We map the complementary \"skills\" pole, from unsupervised reinforcement-learning skill discovery to large-language-model skill libraries, and show that the word \"skill\" is used in at least five distinct senses, of which only the code sense self-improves without gradient updates. We then connect the taxonomy to the emerging skill economy: commercial robot-skill marketplaces now distribute one-tap skills across robots but ship only static playback, which surfaces open problems of adaptation, cross-embodiment portability, provenance, safety verification, composition, and standardisation. This is a deliberately focused survey. Rather than cataloguing the field exhaustively, it examines 77 representative systems across six technique families through one taxonomy and a set of contrast tables, and it supplies operational definitions of the self-improvement mechanisms together with a statement of what each family cannot do.","upvotes":5,"discussionId":"6a76484a8e9301703eaa58b3"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6a742a683d438d7c49c8eaa2","avatarUrl":"/avatars/f7828c23fad2988df910b983e5f466b2.svg","isPro":false,"fullname":"Benjamin Nathaniel Hathorne","user":"Entmarch","type":"user"},{"_id":"6a6a829fa698558ca76157ee","avatarUrl":"/avatars/98e9a42de130397e7f4efce0039cdacd.svg","isPro":false,"fullname":"Richard Williams","user":"richardwilliams","type":"user"},{"_id":"6a6c94b74804b5ea70e1608e","avatarUrl":"/avatars/7976fe663fc956d24044fee1356f0049.svg","isPro":false,"fullname":"Joseph Thomas","user":"Azure-Joseph","type":"user"},{"_id":"6a6da9316d51d01100d3b255","avatarUrl":"/avatars/64c0fad6c030e74ee6203bf7d2d01776.svg","isPro":false,"fullname":"Jennifer Lopez","user":"PrismJennifer","type":"user"},{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"query":{}}">

Cite arxiv.org/abs/2608.01851 in a model README.md to link it from this page.

Cite arxiv.org/abs/2608.01851 in a dataset README.md to link it from this page.

Cite arxiv.org/abs/2608.01851 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.