{"id":1159,"date":"2026-08-28T00:30:30","date_gmt":"2026-08-27T15:30:30","guid":{"rendered":"https:\/\/itexplore.org\/jp\/columns\/ai-agents-robotics-latest-trends-challenges\/"},"modified":"2026-08-28T00:30:30","modified_gmt":"2026-08-27T15:30:30","slug":"ai-agents-robotics-latest-trends-challenges","status":"publish","type":"post","link":"https:\/\/itexplore.org\/jp\/columns\/ai-agents-robotics-latest-trends-challenges\/","title":{"rendered":"AI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3068\u30ed\u30dc\u30c6\u30a3\u30af\u30b9\uff1a\u6700\u65b0\u52d5\u5411\u3068\u8ab2\u984c"},"content":{"rendered":"<p>\u672c\u65e5\u306e\u6ce8\u76eeAI\u30fb\u30c6\u30c3\u30af\u30cb\u30e5\u30fc\u30b9\u3092\u3001\u5c02\u9580\u7684\u306a\u5206\u6790\u3068\u5171\u306b\u304a\u5c4a\u3051\u3057\u307e\u3059\u3002<\/p>\n<div class=\"wp-block-vk-blocks-alert vk_alert alert alert-warning has-alert-icon\">\n<div class=\"vk_alert_icon\">\n<div class=\"vk_alert_icon_icon\"><i class=\"fa-solid fa-triangle-exclamation\" aria-hidden=\"true\"><\/i><\/div>\n<div class=\"vk_alert_icon_text\"><span>Warning<\/span><\/div>\n<\/div>\n<div class=\"vk_alert_content\">\n<p>\u3053\u306e\u8a18\u4e8b\u306fAI\u306b\u3088\u3063\u3066\u81ea\u52d5\u751f\u6210\u30fb\u5206\u6790\u3055\u308c\u305f\u3082\u306e\u3067\u3059\u3002AI\u306e\u6027\u8cea\u4e0a\u3001\u4e8b\u5b9f\u8aa4\u8a8d\u304c\u542b\u307e\u308c\u308b\u53ef\u80fd\u6027\u304c\u3042\u308b\u305f\u3081\u3001\u91cd\u8981\u306a\u5224\u65ad\u3092\u4e0b\u3059\u969b\u306f\u5fc5\u305a\u30ea\u30f3\u30af\u5148\u306e\u4e00\u6b21\u30bd\u30fc\u30b9\u3092\u3054\u78ba\u8a8d\u304f\u3060\u3055\u3044\u3002<\/p>\n<\/div>\n<\/div>\n<div class=\"wp-block-group\" style=\"margin-top:40px;margin-bottom:40px\">\n<h2 class=\"wp-block-heading\">Claude Cowork\u304c\u30c1\u30e3\u30c3\u30c8\u3067\u306e\u6307\u793a\u3092\u8a18\u61b6\u53ef\u80fd\u306b<\/h2>\n<ul>\n<li><strong>\u539f\u984c:<\/strong> Claude Cowork finally remembers what you told the app in chat | TechCrunch<\/li>\n<\/ul>\n<h3 class=\"wp-block-heading\">\u5c02\u9580\u30a2\u30ca\u30ea\u30b9\u30c8\u306e\u5206\u6790<\/h3>\n<div class=\"ai-summary-content\">\n<p>\u3053\u306eTechCrunch\u306e\u8a18\u4e8b\u306f\u3001\u30a2\u30af\u30bb\u30b9\u5236\u9650\uff08\u30da\u30a4\u30a6\u30a9\u30fc\u30eb\u3001\u30ed\u30b0\u30a4\u30f3\u8981\u4ef6\u306a\u3069\uff09\u306e\u305f\u3081\u3001\u8a73\u7d30\u306a\u5185\u5bb9\u3092\u76f4\u63a5\u53d6\u5f97\u3067\u304d\u307e\u305b\u3093\u3067\u3057\u305f\u3002<\/p>\n<p>\u3057\u304b\u3057\u3001\u30bf\u30a4\u30c8\u30eb\u304b\u3089\u5224\u65ad\u3059\u308b\u3068\u3001<strong>Anthropic<\/strong>\u306eAI\u30a2\u30b7\u30b9\u30bf\u30f3\u30c8\u300c<strong>Claude Cowork<\/strong>\u300d\u304c\u3001\u30e6\u30fc\u30b6\u30fc\u3068\u306e\u30c1\u30e3\u30c3\u30c8\u5c65\u6b74\u3084\u4ee5\u524d\u306e\u6307\u793a\u3092\u3088\u308a\u52b9\u679c\u7684\u306b\u8a18\u61b6\u3057\u3001\u6587\u8108\u3092\u7dad\u6301\u3067\u304d\u308b\u3088\u3046\u6539\u5584\u3055\u308c\u305f\u3053\u3068\u3092\u5831\u3058\u3066\u3044\u308b\u3068\u63a8\u6e2c\u3055\u308c\u307e\u3059\u3002\u3053\u308c\u306f\u3001<strong>LLM<\/strong>\u306e\u9577\u671f\u7684\u306a\u5bfe\u8a71\u80fd\u529b\u3068<strong>AI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8<\/strong>\u306e\u6a5f\u80fd\u6027\u5411\u4e0a\u306b\u304a\u3044\u3066\u91cd\u8981\u306a\u9032\u6b69\u3092\u793a\u5506\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\ud83d\udc49 <strong><a href=\"https:\/\/techcrunch.com\/2026\/08\/25\/claude-cowork-finally-remembers-what-you-told-the-app-in-chat\/\" target=\"_blank\" rel=\"noopener\">TechCrunch \u3067\u8a18\u4e8b\u5168\u6587\u3092\u8aad\u3080<\/a><\/strong><\/p>\n<\/div>\n<ul>\n<li><strong>\u8981\u70b9:<\/strong> Claude Cowork\u306e\u8a18\u61b6\u529b\u5411\u4e0a\u306f\u3001LLM\u306e\u9577\u671f\u7684\u306a\u5bfe\u8a71\u80fd\u529b\u3068AI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u6587\u8108\u7406\u89e3\u3092\u5927\u304d\u304f\u9032\u5c55\u3055\u305b\u308b\u3002<\/li>\n<li><strong>\u8457\u8005:<\/strong> Sarah Perez<\/li>\n<\/ul>\n<blockquote class=\"wp-block-quote\"><p><span>English Summary:<\/span><\/p>\n<p>This TechCrunch article could not be directly accessed for detailed content due to access restrictions (paywalls, login requirements, etc.).<\/p>\n<p>However, based on the title, it is inferred that <strong>Anthropic's<\/strong> AI assistant, <strong>Claude Cowork<\/strong>, has been improved to more effectively remember user chat history and previous instructions, thereby maintaining context. This suggests a significant advancement in the long-term conversational capabilities of <strong>LLMs<\/strong> and the functionality of <strong>AI agents<\/strong>.<\/p>\n<\/blockquote>\n<\/div>\n<div class=\"wp-block-group\" style=\"margin-top:40px;margin-bottom:40px\">\n<h2 class=\"wp-block-heading\">Prime Agent: \u81ea\u5df1\u6539\u5584\u578bRLM\u30cf\u30fc\u30cd\u30b9<\/h2>\n<ul>\n<li><strong>\u539f\u984c:<\/strong> Prime Agent: A Self-Improving RLM Harness<\/li>\n<\/ul>\n<h3 class=\"wp-block-heading\">\u5c02\u9580\u30a2\u30ca\u30ea\u30b9\u30c8\u306e\u5206\u6790<\/h3>\n<div class=\"ai-summary-content\">\n<p>\u300c<strong>Prime Agent<\/strong>\u300d\u306f\u3001\u8a00\u8a9e\u30e2\u30c7\u30eb\u304c\u6301\u3064\u30b7\u30fc\u30b1\u30f3\u30b7\u30e3\u30eb\u51e6\u7406\u306e\u9650\u754c\u3092\u8d85\u3048\u3001\u5916\u90e8\u60c5\u5831\u3068\u8a08\u7b97\u3092\u6d3b\u7528\u3057\u3066\u9577\u671f\u9593\u306b\u308f\u305f\u308b\u30a8\u30fc\u30b8\u30a7\u30f3\u30b7\u30fc\u3092\u5b9f\u73fe\u3059\u308b\u305f\u3081\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30cf\u30fc\u30cd\u30b9\u3067\u3059\u3002\u3053\u308c\u306f\u3001\u30d7\u30ed\u30b0\u30e9\u30e0\u306b\u3088\u308b\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u51e6\u7406\u3068\u30c6\u30b9\u30c8\u6642\u306e\u8a08\u7b97\u306e\u305f\u3081\u306b\u3001\u6c38\u7d9a\u7684\u306a<strong>IPython REPL<\/strong>\u3092\u4ecb\u3057\u3066<strong>Recursive Language Model<\/strong> (RLM) \u306e\u62bd\u8c61\u5316\u306b\u5f93\u3044\u307e\u3059\u3002<\/p>\n<p><strong>Continual Harness<\/strong>\u306f\u3001\u5c65\u6b74\u3001\u8a18\u61b6\u3001\u30b9\u30ad\u30eb\u3001\u30d7\u30ed\u30f3\u30d7\u30c8\u3001\u304a\u3088\u3073\u30b5\u30d6\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u4ed5\u69d8\u3092\u8ecc\u8de1\u5168\u4f53\u306b\u308f\u305f\u3063\u3066\u4fdd\u6301\u3057\u307e\u3059\u3002\u518d\u5e30\u7684\u306a\u30b5\u30d6\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306f\u76f4\u63a5\u7684\u306a\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u9593\u901a\u4fe1\u3092\u901a\u3058\u3066\u9023\u643a\u3057\u3001<strong>Agents View<\/strong>\u306b\u3088\u308a\u4eba\u9593\u304c\u30c7\u30fc\u30e2\u30f3\u30d0\u30c3\u30af\u30a2\u30c3\u30d7\u3055\u308c\u305f\u30bb\u30c3\u30b7\u30e7\u30f3\u3092\u691c\u67fb\u304a\u3088\u3073\u7ba1\u7406\u3067\u304d\u307e\u3059\u3002<strong>Prime Agent<\/strong>\u306f\u3001\u5b9f\u884c\u3001\u56de\u5fa9\u3001\u691c\u8a3c\u3001\u304a\u3088\u3073\u30ea\u30bd\u30fc\u30b9\u7ba1\u7406\u3092\u6a19\u6e96\u5316\u3057\u3064\u3064\u3001\u6226\u7565\u69cb\u7bc9\u306f\u30e2\u30c7\u30eb\u306b\u59d4\u306d\u307e\u3059\u3002<\/p>\n<p>\u3053\u306e\u30cf\u30fc\u30cd\u30b9\u306f\u3001\u30cf\u30fc\u30cd\u30b9\u306e\u969c\u5bb3\u304c\u30e2\u30c7\u30eb\u306e\u969c\u5bb3\u306b\u306a\u308b\u306e\u3092\u9632\u304e\u3001\u30e2\u30c7\u30eb\u306e\u771f\u306e\u6700\u5927\u57fa\u76e4\u80fd\u529b\u3078\u306e\u6e2c\u5b9a\u3092\u63a8\u9032\u3057\u307e\u3059\u3002<strong>Prime Agent<\/strong>\u306f\u3001<strong>ARC-AGI-3 RHAE Best@1<\/strong>\u306e\u30b9\u30b3\u30a2\u309230%\u304b\u3089<strong>95.5%<\/strong>\u306b\u5411\u4e0a\u3055\u305b\u3001\u9577\u6587\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u3001GPU\u30ab\u30fc\u30cd\u30eb\u751f\u6210\u3001\u30a8\u30df\u30e5\u30ec\u30fc\u30bf\u69cb\u7bc9\u3001\u81ea\u5f8b\u578bnanoGPT\u30b9\u30d4\u30fc\u30c9\u30e9\u30f3\u306a\u3069\u3001\u30cd\u30a4\u30c6\u30a3\u30d6\u304a\u3088\u3073\u4e00\u822c\u7684\u306a\u30cf\u30fc\u30cd\u30b9\u3092\u51cc\u99d5\u307e\u305f\u306f\u540c\u7b49\u4ee5\u4e0a\u306e\u6027\u80fd\u3092\u767a\u63ee\u3057\u307e\u3059\u3002<strong>Factorio<\/strong>\u306e\u4e8b\u4f8b\u3067\u306f\u3001\u6d17\u7df4\u3055\u308c\u305f\u6280\u8853\u306e\u7d99\u7d9a\u7684\u306a\u9032\u6b69\u3068\u3001\u5c02\u7528\u30b5\u30d6\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306b\u3088\u308b\u4e26\u5217\u4f5c\u696d\u304c\u53ef\u80fd\u306b\u306a\u308b\u3053\u3068\u304c\u793a\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u30b3\u30fc\u30c9\u306fGitHub\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\ud83d\udc49 <strong><a href=\"https:\/\/arxiv.org\/abs\/2608.23552\" target=\"_blank\" rel=\"noopener\">arXiv \u3067\u8a18\u4e8b\u5168\u6587\u3092\u8aad\u3080<\/a><\/strong><\/p>\n<\/div>\n<ul>\n<li><strong>\u8981\u70b9:<\/strong> Prime Agent\u306f\u3001\u5916\u90e8\u30c4\u30fc\u30eb\u3068\u518d\u5e30\u7684\u30b5\u30d6\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092\u6d3b\u7528\u3057\u3001LLM\u306e\u9577\u671f\u7684\u306a\u81ea\u5f8b\u6027\u3068\u8907\u96d1\u306a\u30bf\u30b9\u30af\u5b9f\u884c\u80fd\u529b\u3092\u5927\u5e45\u306b\u5411\u4e0a\u3055\u305b\u308b\u81ea\u5df1\u6539\u5584\u578b\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30cf\u30fc\u30cd\u30b9\u3067\u3042\u308b\u3002<\/li>\n<li><strong>\u8457\u8005:<\/strong> Seth Karten, Alex L. Zhang, Kevin Thomas, Sebastian M\u00fcller, Elie Bakouch, Daniel Auras, Mika Senghaas, Fares Obeid, Konstantin Dunas, Johannes Hagemann, Sami Jaghouar<\/li>\n<\/ul>\n<blockquote class=\"wp-block-quote\"><p><span>English Summary:<\/span><\/p>\n<p><strong>Prime Agent<\/strong> is an open-source harness designed to enable long-horizon agency for language models, extending beyond their sequential processing limitations by leveraging external information and computation. It adheres to the <strong>Recursive Language Model<\/strong> (RLM) abstraction through a persistent <strong>IPython REPL<\/strong> for programmatic context processing and test-time compute.<\/p>\n<p>The <strong>Continual Harness<\/strong> component preserves histories, memories, skills, prompts, and subagent specifications across trajectories. Recursive subagents coordinate via direct agent-to-agent communication, and the <strong>Agents View<\/strong> allows humans to inspect and manage daemon-backed sessions. <strong>Prime Agent<\/strong> standardizes execution, recovery, verification, and resource accounting, while leaving strategy construction to the model itself.<\/p>\n<p>This low-friction, expressive membrane prevents harness failures from becoming model failures, pushing measurement towards the model's true maximal underlying capability. <strong>Prime Agent<\/strong> significantly boosts <strong>ARC-AGI-3 RHAE Best@1<\/strong> from 30% to <strong>95.5%<\/strong>, and matches or exceeds native and popular harnesses in tasks like long-context coding, GPU-kernel generation, emulator construction, and autonomous nanoGPT speedruns. In the context of <strong>Factorio<\/strong>, it demonstrates continuous technology progression through refinement and parallelized work via dedicated subagents. The code is publicly available on GitHub.<\/p>\n<\/blockquote>\n<\/div>\n<div class=\"wp-block-group\" style=\"margin-top:40px;margin-bottom:40px\">\n<h2 class=\"wp-block-heading\">\u30ed\u30dc\u30c6\u30a3\u30af\u30b9\u30b9\u30bf\u30fc\u30c8\u30a2\u30c3\u30d7Generalist\u304c30\u5104\u30c9\u30eb\u306e\u8a55\u4fa1\u984d\u306b\u5230\u9054<\/h2>\n<ul>\n<li><strong>\u539f\u984c:<\/strong> Robotics startup Generalist reaches $3B valuation, sources say | TechCrunch<\/li>\n<\/ul>\n<h3 class=\"wp-block-heading\">\u5c02\u9580\u30a2\u30ca\u30ea\u30b9\u30c8\u306e\u5206\u6790<\/h3>\n<div class=\"ai-summary-content\">\n<p>\u3053\u306eTechCrunch\u306e\u8a18\u4e8b\u306f\u3001\u30a2\u30af\u30bb\u30b9\u5236\u9650\uff08\u30da\u30a4\u30a6\u30a9\u30fc\u30eb\u3001\u30ed\u30b0\u30a4\u30f3\u8981\u4ef6\u306a\u3069\uff09\u306e\u305f\u3081\u3001\u8a73\u7d30\u306a\u5185\u5bb9\u3092\u76f4\u63a5\u53d6\u5f97\u3067\u304d\u307e\u305b\u3093\u3067\u3057\u305f\u3002<\/p>\n<p>\u3057\u304b\u3057\u3001\u30bf\u30a4\u30c8\u30eb\u304b\u3089\u5224\u65ad\u3059\u308b\u3068\u3001\u30ed\u30dc\u30c6\u30a3\u30af\u30b9\u5206\u91ce\u306e\u30b9\u30bf\u30fc\u30c8\u30a2\u30c3\u30d7\u300c<strong>Generalist<\/strong>\u300d\u304c\u3001\u60c5\u5831\u7b4b\u306b\u3088\u308b\u3068<strong>30\u5104\u30c9\u30eb<\/strong>\u306e\u8a55\u4fa1\u984d\u306b\u9054\u3057\u305f\u3053\u3068\u3092\u5831\u3058\u3066\u3044\u308b\u3068\u63a8\u6e2c\u3055\u308c\u307e\u3059\u3002\u3053\u308c\u306f\u3001<strong>AI<\/strong>\u3068<strong>\u30ed\u30dc\u30c6\u30a3\u30af\u30b9<\/strong>\u306e\u878d\u5408\u304c\u6025\u901f\u306b\u9032\u5c55\u3057\u3001\u3053\u306e\u5206\u91ce\u3078\u306e\u6295\u8cc7\u304c\u6d3b\u767a\u3067\u3042\u308b\u3053\u3068\u3092\u793a\u3057\u3066\u304a\u308a\u3001\u7279\u306b\u6c4e\u7528\u7684\u306a\u30ed\u30dc\u30c3\u30c8\u6280\u8853\u3084<strong>AI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8<\/strong>\u304c\u7269\u7406\u4e16\u754c\u3067\u30bf\u30b9\u30af\u3092\u5b9f\u884c\u3059\u308b\u80fd\u529b\u3078\u306e\u671f\u5f85\u304c\u9ad8\u307e\u3063\u3066\u3044\u308b\u3053\u3068\u3092\u53cd\u6620\u3057\u3066\u3044\u308b\u53ef\u80fd\u6027\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n<p>\ud83d\udc49 <strong><a href=\"https:\/\/techcrunch.com\/2026\/08\/25\/robotics-startup-generalist-reaches-3b-valuation-sources-say\/\" target=\"_blank\" rel=\"noopener\">TechCrunch \u3067\u8a18\u4e8b\u5168\u6587\u3092\u8aad\u3080<\/a><\/strong><\/p>\n<\/div>\n<ul>\n<li><strong>\u8981\u70b9:<\/strong> \u30ed\u30dc\u30c6\u30a3\u30af\u30b9\u30b9\u30bf\u30fc\u30c8\u30a2\u30c3\u30d7Generalist\u306e30\u5104\u30c9\u30eb\u8a55\u4fa1\u984d\u306f\u3001AI\u3068\u30ed\u30dc\u30c6\u30a3\u30af\u30b9\u5206\u91ce\u3078\u306e\u5927\u898f\u6a21\u306a\u6295\u8cc7\u3068\u3001\u6c4e\u7528\u30ed\u30dc\u30c3\u30c8\u6280\u8853\u3078\u306e\u9ad8\u3044\u671f\u5f85\u3092\u6d6e\u304d\u5f6b\u308a\u306b\u3059\u308b\u3002<\/li>\n<li><strong>\u8457\u8005:<\/strong> Marina Temkin<\/li>\n<\/ul>\n<blockquote class=\"wp-block-quote\"><p><span>English Summary:<\/span><\/p>\n<p>This TechCrunch article could not be directly accessed for detailed content due to access restrictions (paywalls, login requirements, etc.).<\/p>\n<p>However, based on the title, it is inferred that the robotics startup <strong>Generalist<\/strong> has reportedly reached a <strong>$3 billion valuation<\/strong>, according to sources. This indicates rapid advancements and significant investment in the convergence of <strong>AI<\/strong> and <strong>robotics<\/strong>, potentially reflecting high expectations for general-purpose robotic technologies and the ability of <strong>AI agents<\/strong> to perform tasks in the physical world.<\/p>\n<\/blockquote>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Prime Agent\u306b\u3088\u308b\u81ea\u5df1\u6539\u5584\u578bRLM\u30cf\u30fc\u30cd\u30b9\u306e\u9032\u5316\u3068\u3001Anthropic\u306eClaude Cowork\u306e\u8a18\u61b6\u529b\u5411\u4e0a\u3001\u305d\u3057\u3066Generalist\u306e\u30ed\u30dc\u30c6\u30a3\u30af\u30b9\u5206\u91ce\u3067\u306e\u8a55\u4fa1\u984d\u6025\u4e0a\u6607\u306b\u95a2\u3059\u308b\u6700\u65b0AI\u30cb\u30e5\u30fc\u30b9\u3092\u6df1\u6398\u308a\u3057\u307e\u3059\u3002<\/p>\n","protected":false},"author":1,"featured_media":6,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"sns_share_botton_hide":"","vkExUnit_sns_title":"","_vk_print_noindex":"","sitemap_hide":"","_veu_custom_css":"","veu_display_promotion_alert":"","vkexunit_cta_each_option":"","_lightning_design_setting":[],"footnotes":""},"categories":[3],"tags":[8,17,58,16,578,51,26,15],"class_list":["post-1159","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-columns","tag-ai","tag-anthropic","tag-llm","tag-prime-agent","tag-51","tag-26"],"veu_head_title_object":{"title":"","add_site_title":""},"_links":{"self":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/posts\/1159","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/comments?post=1159"}],"version-history":[{"count":0,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/posts\/1159\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/media\/6"}],"wp:attachment":[{"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/media?parent=1159"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/categories?post=1159"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/itexplore.org\/jp\/wp-json\/wp\/v2\/tags?post=1159"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}