{"id":7480,"date":"2025-09-25T06:41:00","date_gmt":"2025-09-24T21:41:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7480"},"modified":"2025-09-21T14:47:30","modified_gmt":"2025-09-21T05:47:30","slug":"teaching-llms-to-plan-logical-chain-of-thought-instruction-tuning-for-symbolic-planning","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7480","title":{"rendered":"Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning\u00a0<\/strong>[23.2]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u3001\u69d8\u3005\u306a\u30bf\u30b9\u30af\u306b\u307e\u305f\u304c\u308b\u5370\u8c61\u7684\u306a\u6a5f\u80fd\u3092\u793a\u3057\u3066\u3044\u308b\u304c\u3001\u69cb\u9020\u5316\u3055\u308c\u305f\u30b7\u30f3\u30dc\u30ea\u30c3\u30af\u30d7\u30e9\u30f3\u30cb\u30f3\u30b0\u3092\u5b9f\u884c\u3059\u308b\u80fd\u529b\u306f\u307e\u3060\u9650\u3089\u308c\u3066\u3044\u308b\u3002 \u8ad6\u7406\u7684\u9023\u9396\u63a8\u8ad6\u306b\u3088\u308aLLM\u306e\u30b7\u30f3\u30dc\u30ea\u30c3\u30af\u30d7\u30e9\u30f3\u30cb\u30f3\u30b0\u80fd\u529b\u3092\u9ad8\u3081\u308b\u305f\u3081\u306b\u8a2d\u8a08\u3055\u308c\u305f\u65b0\u3057\u3044\u547d\u4ee4\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30afPDDL-Instruct\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2509.13351v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2509.13351v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sun, 14 Sep 2025 02:42:34 GMT)<\/li>\n\n\n\n<li>\u300cWe have presented PDDL-INSTRUCT, a novel framework that significantly enhances the symbolic planning capabilities of Large Language Models through logical chain-of-thought instruction tuning. By decomposing the planning process into verifiable logical reasoning chains and providing explicit verification feedback, our approach enables LLMs to generate valid plans with unprecedented reliability across diverse planning domains.\u300d\u3068\u5de5\u592b\u3057\u305f\u5f62\u306e\u8a08\u753b\u4f5c\u6210\u7528PostTraining<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[636],"class_list":["post-7480","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-636"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7480","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7480"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7480\/revisions"}],"predecessor-version":[{"id":7481,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7480\/revisions\/7481"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7480"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7480"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7480"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}