{"id":10380,"date":"2024-02-28T10:18:11","date_gmt":"2024-02-28T10:18:11","guid":{"rendered":"https:\/\/dailyai.com\/?p=10380"},"modified":"2024-02-28T10:18:11","modified_gmt":"2024-02-28T10:18:11","slug":"meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls","status":"publish","type":"post","link":"https:\/\/dailyai.com\/ru\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/","title":{"rendered":"Meta, UCSD \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 ToolVerifier \u0434\u043b\u044f \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044f \u0432\u044b\u0437\u043e\u0432\u043e\u0432 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432 LLM"},"content":{"rendered":"<p><strong>\u0418\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0438\u0437 Meta \u0438 \u041a\u0430\u043b\u0438\u0444\u043e\u0440\u043d\u0438\u0439\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u0432 \u0421\u0430\u043d-\u0414\u0438\u0435\u0433\u043e (UCSD) \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0430\u043b\u0438 ToolVerifier, \u043c\u0435\u0442\u043e\u0434, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0443\u043b\u0443\u0447\u0448\u0430\u0435\u0442 \u0442\u043e, \u043a\u0430\u043a LLM \u0432\u044b\u0437\u044b\u0432\u0430\u044e\u0442 \u0438 \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u0443\u044e\u0442 \u0441 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u044b\u043c\u0438 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043c\u0438.<\/strong><\/p>\n<p>\u0414\u043b\u044f \u0442\u043e\u0433\u043e \u0447\u0442\u043e\u0431\u044b \u043c\u0430\u0433\u0438\u0441\u0442\u0440\u0430\u043d\u0442\u044b \u0441\u0442\u0430\u043b\u0438 \u043f\u043e\u043b\u0435\u0437\u043d\u044b\u043c\u0438 \u0432 \u043a\u0430\u0447\u0435\u0441\u0442\u0432\u0435 \u0430\u0441\u0441\u0438\u0441\u0442\u0435\u043d\u0442\u043e\u0432 \u0438\u043b\u0438 <a href=\"https:\/\/dailyai.com\/ru\/2024\/01\/can-we-increase-visibility-into-ai-agents-to-make-them-safer\/\">\u0430\u0433\u0435\u043d\u0442\u044b<\/a>\u0418\u0445 \u043d\u0443\u0436\u043d\u043e \u043d\u0430\u0443\u0447\u0438\u0442\u044c \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c\u0441\u044f \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u043c\u0438 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043c\u0438 \u0438\u043b\u0438 API. \u0422\u043e\u043d\u043a\u0430\u044f \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0430 LLM \u043d\u0430 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u043a\u043e\u043d\u043a\u0440\u0435\u0442\u043d\u043e\u0433\u043e \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430 \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442, \u043d\u043e \u0440\u0435\u0430\u043b\u044c\u043d\u0430\u044f \u0437\u0430\u0434\u0430\u0447\u0430 \u0441\u043e\u0441\u0442\u043e\u0438\u0442 \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e\u0431\u044b LLM \u043c\u043e\u0433 \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u043e\u0432\u0430\u0442\u044c \u0441 \u043d\u043e\u0432\u044b\u043c\u0438 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043c\u0438 \u0431\u0435\u0437 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e\u0441\u0442\u0438 \u0442\u043e\u043d\u043a\u043e\u0439 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0438 \u0438\u043b\u0438 \u0434\u0435\u043c\u043e\u043d\u0441\u0442\u0440\u0430\u0446\u0438\u0438 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u043a\u0430\u0434\u0440\u043e\u0432.<\/p>\n<p>\u041a\u043e\u0433\u0434\u0430 \u0434\u0432\u0430 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430 \u043e\u0447\u0435\u043d\u044c \u043f\u043e\u0445\u043e\u0436\u0438, LLM \u043c\u043e\u0436\u0435\u0442 \u0431\u044b\u0442\u044c \u043e\u0441\u043e\u0431\u0435\u043d\u043d\u043e \u0441\u043b\u043e\u0436\u043d\u043e \u0432\u044b\u0431\u0440\u0430\u0442\u044c \u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u044b\u0439 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442 \u0434\u043b\u044f \u0434\u043e\u0441\u0442\u0438\u0436\u0435\u043d\u0438\u044f \u0441\u0432\u043e\u0435\u0439 \u0446\u0435\u043b\u0438. \u0422\u0435\u043a\u0443\u0449\u0438\u0439 \u043c\u0435\u0442\u043e\u0434 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u043f\u0440\u0438\u043c\u0435\u0440\u043e\u0432 \u0441 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u043c\u0438 \u0441\u043d\u0438\u043c\u043a\u0430\u043c\u0438 \u0434\u043b\u044f \u043a\u0430\u0436\u0434\u043e\u0433\u043e \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430 \u043c\u043e\u0436\u0435\u0442 \u0437\u0430\u043d\u0438\u043c\u0430\u0442\u044c \u0431\u043e\u043b\u044c\u0448\u0443\u044e \u0447\u0430\u0441\u0442\u044c \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u043d\u043e\u0433\u043e \u043e\u043a\u043d\u0430, \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u043e\u0433\u043e LLM.<\/p>\n<p>ToolVerifier - \u044d\u0442\u043e \u043c\u0435\u0442\u043e\u0434 \u0441\u0430\u043c\u043e\u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0438, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u0435\u0442 LLM \u0437\u0430\u0434\u0430\u0432\u0430\u0442\u044c \u0441\u0435\u0431\u0435 \u0432\u043e\u043f\u0440\u043e\u0441\u044b, \u0447\u0442\u043e\u0431\u044b \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0438\u0442\u044c, \u043a\u0430\u043a\u043e\u0439 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0438 \u043a\u0430\u043a\u0438\u0435 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b \u0435\u043c\u0443 \u043f\u0435\u0440\u0435\u0434\u0430\u0432\u0430\u0442\u044c.<\/p>\n<p>\u0427\u0442\u043e\u0431\u044b \u043f\u043e\u043c\u043e\u0447\u044c LLM, ToolVerifier \u0441\u043d\u0430\u0447\u0430\u043b\u0430 \u0432\u044b\u0431\u0438\u0440\u0430\u0435\u0442 \u043d\u0430\u0438\u0431\u043e\u043b\u0435\u0435 \u043f\u043e\u0434\u0445\u043e\u0434\u044f\u0449\u0438\u0439 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442 \u0438\u0437 \u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0438 \u0432\u0430\u0440\u0438\u0430\u043d\u0442\u043e\u0432, \u0430 \u0437\u0430\u0442\u0435\u043c \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u0443\u0435\u0442 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u044e\u0449\u0438\u0435 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u044b. \u041d\u0430 \u043a\u0430\u0436\u0434\u043e\u043c \u0438\u0437 \u044d\u0442\u0438\u0445 \u044d\u0442\u0430\u043f\u043e\u0432 \u043e\u043d \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u0443\u0435\u0442 \u0432\u043e\u043f\u0440\u043e\u0441\u044b, \u0447\u0442\u043e\u0431\u044b \u043f\u043e\u043c\u043e\u0447\u044c \u043e\u0446\u0435\u043d\u0438\u0442\u044c \u0441\u0432\u043e\u0439 \u0432\u044b\u0431\u043e\u0440 \u0438 \u043e\u0442\u043b\u0438\u0447\u0438\u0442\u044c \u043f\u043e\u0445\u043e\u0436\u0438\u0435 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u044b-\u043a\u0430\u043d\u0434\u0438\u0434\u0430\u0442\u044b.<\/p>\n<p>\u0412\u043e\u0442 \u043f\u0440\u0438\u043c\u0435\u0440 \u0438\u0437 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044c\u0441\u043a\u043e\u0439 \u0440\u0430\u0431\u043e\u0442\u044b, \u043f\u043e\u043a\u0430\u0437\u044b\u0432\u0430\u044e\u0449\u0438\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441 \u0432\u044b\u0431\u043e\u0440\u0430 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430 \u0438 \u0443\u0442\u043e\u0447\u043d\u0435\u043d\u0438\u044f \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432.<\/p>\n<figure id=\"attachment_10387\" aria-describedby=\"caption-attachment-10387\" style=\"width: 1528px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-10387\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example.png\" alt=\"\" width=\"1528\" height=\"682\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example.png 1528w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-300x134.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-1024x457.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-768x343.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-370x165.png 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-800x357.png 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-740x330.png 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-20x9.png 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-example-108x48.png 108w\" sizes=\"auto, (max-width: 1528px) 100vw, 1528px\" \/><figcaption id=\"caption-attachment-10387\" class=\"wp-caption-text\">ToolVerifier \u0441\u043d\u0430\u0447\u0430\u043b\u0430 \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u044f\u0435\u0442 \u0434\u0432\u0430 \u043b\u0443\u0447\u0448\u0438\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430 \u0438 \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u0443\u0435\u0442 \u043f\u0440\u043e\u0432\u0435\u0440\u043e\u0447\u043d\u044b\u0439 \u0432\u043e\u043f\u0440\u043e\u0441. \u041e\u0442\u0432\u0435\u0442 \u043d\u0430 \u0432\u043e\u043f\u0440\u043e\u0441 \u043f\u0440\u0438\u0432\u043e\u0434\u0438\u0442 \u043a \u043e\u043a\u043e\u043d\u0447\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u043c\u0443 \u0432\u044b\u0431\u043e\u0440\u0443 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430. \u0410\u043d\u0430\u043b\u043e\u0433\u0438\u0447\u043d\u044b\u0439 \u043c\u0435\u0442\u043e\u0434 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u0442\u0441\u044f \u0434\u043b\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432. \u0418\u0441\u0442\u043e\u0447\u043d\u0438\u043a: arXiv<\/figcaption><\/figure>\n<p>ToolVerifier \u0431\u044b\u043b \u043e\u0431\u0443\u0447\u0435\u043d \u043d\u0430 \u0434\u0430\u043d\u043d\u044b\u0445, \u0441\u043e\u0441\u0442\u043e\u044f\u0449\u0438\u0445 \u0438\u0437 \u0441\u043f\u0438\u0441\u043a\u0430 \u0441\u0438\u043d\u0442\u0435\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432, \u0432\u043a\u043b\u044e\u0447\u0430\u044f \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u044b \u0434\u043b\u044f \u043f\u0443\u0442\u0435\u0448\u0435\u0441\u0442\u0432\u0438\u0439, \u0431\u0430\u043d\u043a\u043e\u0432\u0441\u043a\u0438\u0445 \u043e\u043f\u0435\u0440\u0430\u0446\u0438\u0439 \u0438 \u043a\u0430\u043b\u0435\u043d\u0434\u0430\u0440\u044f, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0438\u0445 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u044f. \u041e\u043d \u0431\u044b\u043b \u043e\u0431\u0443\u0447\u0435\u043d \u0432\u044b\u0431\u0438\u0440\u0430\u0442\u044c \u043f\u043e\u0434\u0445\u043e\u0434\u044f\u0449\u0438\u0439 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442, \u043e\u0441\u043d\u043e\u0432\u044b\u0432\u0430\u044f\u0441\u044c \u0438\u0441\u043a\u043b\u044e\u0447\u0438\u0442\u0435\u043b\u044c\u043d\u043e \u043d\u0430 \u043d\u0430\u0437\u0432\u0430\u043d\u0438\u0438 \u0438 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u0438.<\/p>\n<p>\u041f\u043e\u0441\u043b\u0435 \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0432\u044b\u0431\u043e\u0440\u0443 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432 \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0435 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u043f\u0440\u043e\u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u043b\u0438 ToolVerifier \u043d\u0430 4 \u0437\u0430\u0434\u0430\u0447\u0430\u0445 \u0438\u0437 \u0431\u0435\u043d\u0447\u043c\u0430\u0440\u043a\u0430 ToolBench, \u0432 \u043a\u043e\u0442\u043e\u0440\u044b\u0445 Llama 2-70B \u0434\u043e\u043b\u0436\u043d\u0430 \u0431\u044b\u043b\u0430 \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u043e\u0432\u0430\u0442\u044c \u0441 17 \u0440\u0430\u043d\u0435\u0435 \u043d\u0435\u0432\u0438\u0434\u0430\u043d\u043d\u044b\u043c\u0438 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043c\u0438.<\/p>\n<p>\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b <a href=\"https:\/\/arxiv.org\/pdf\/2402.14158.pdf\" target=\"_blank\" rel=\"noopener\">\u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d\u043e \u0432 \u0433\u0430\u0437\u0435\u0442\u0435<\/a> \u0443\u0442\u0432\u0435\u0440\u0436\u0434\u0430\u044e\u0442, \u0447\u0442\u043e \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u043c\u0435\u0442\u043e\u0434\u0430 ToolVerifier \u043f\u0440\u0438\u0432\u0435\u043b\u043e \u043a \"\u0441\u0440\u0435\u0434\u043d\u0435\u043c\u0443 \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044e \u043d\u0430 22% \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u0431\u0430\u0437\u043e\u0432\u044b\u043c\u0438 \u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f\u043c\u0438 \u0432 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0432\u044b\u0441\u0442\u0440\u0435\u043b\u043e\u0432, \u0434\u0430\u0436\u0435 \u0432 \u0441\u0446\u0435\u043d\u0430\u0440\u0438\u044f\u0445, \u0433\u0434\u0435 \u0440\u0430\u0437\u043b\u0438\u0447\u0438\u044f \u043c\u0435\u0436\u0434\u0443 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043c\u0438-\u043a\u0430\u043d\u0434\u0438\u0434\u0430\u0442\u0430\u043c\u0438 \u043e\u0447\u0435\u043d\u044c \u0442\u043e\u043d\u043a\u0438\u0435\".<\/p>\n<figure id=\"attachment_10389\" aria-describedby=\"caption-attachment-10389\" style=\"width: 1396px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"size-full wp-image-10389\" src=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison.png\" alt=\"\" width=\"1396\" height=\"566\" srcset=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison.png 1396w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-300x122.png 300w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-1024x415.png 1024w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-768x311.png 768w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-370x150.png 370w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-800x324.png 800w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-740x300.png 740w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-20x8.png 20w, https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/ToolVerifier-comparison-118x48.png 118w\" sizes=\"auto, (max-width: 1396px) 100vw, 1396px\" \/><figcaption id=\"caption-attachment-10389\" class=\"wp-caption-text\">\u041f\u0440\u043e\u0446\u0435\u043d\u0442\u043d\u043e\u0435 \u0441\u043e\u043e\u0442\u043d\u043e\u0448\u0435\u043d\u0438\u0435 (%) \u0443\u0441\u043f\u0435\u0448\u043d\u043e\u0441\u0442\u0438 \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u0437\u0430\u0434\u0430\u0447 Weather, Booking, Home \u0438 Cat \u0438\u0437 \u0431\u0435\u043d\u0447\u043c\u0430\u0440\u043a\u0430 Toolbench \u043f\u0440\u0438 \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0441 ToolVerifier \u0438 \u0431\u0435\u0437 \u043d\u0435\u0433\u043e. \u0418\u0441\u0442\u043e\u0447\u043d\u0438\u043a: arXiv<\/figcaption><\/figure>\n<p>\u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b \u043f\u043e\u043a\u0430\u0437\u044b\u0432\u0430\u044e\u0442, \u0447\u0442\u043e ToolVerifier \u043e\u0431\u0435\u0441\u043f\u0435\u0447\u0438\u0432\u0430\u0435\u0442 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0435 \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u0435 \u0432\u044b\u0431\u043e\u0440\u0430 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432 LLM \u0438 \u0442\u043e\u0447\u043d\u0443\u044e \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u044e \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u043e\u0432. \u041c\u0435\u0442\u043e\u0434 \u0431\u044b\u043b \u043e\u0431\u0443\u0447\u0435\u043d \u0438 \u043f\u0440\u043e\u0442\u0435\u0441\u0442\u0438\u0440\u043e\u0432\u0430\u043d \u0442\u043e\u043b\u044c\u043a\u043e \u0434\u043b\u044f \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u0438\u044f \u043e\u0434\u043d\u043e\u0433\u043e, \u0430 \u043d\u0435 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432, \u043d\u043e, \u0442\u0435\u043c \u043d\u0435 \u043c\u0435\u043d\u0435\u0435, \u043e\u043d \u043c\u043d\u043e\u0433\u043e\u043e\u0431\u0435\u0449\u0430\u044e\u0449\u0438\u0439.<\/p>\n<p>\u041b\u041b\u041c \u0441 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043b\u044c\u043d\u044b\u043c \u0434\u043e\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u0435\u043c - \u044d\u0442\u043e \u0437\u0430\u0445\u0432\u0430\u0442\u044b\u0432\u0430\u044e\u0449\u0435\u0435 \u0440\u0430\u0437\u0432\u0438\u0442\u0438\u0435 \u0432 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0438 \u0418\u0418 \u0432 \u043a\u0430\u0447\u0435\u0441\u0442\u0432\u0435 \u043e\u0431\u043e\u0431\u0449\u0435\u043d\u043d\u043e\u0433\u043e \u0430\u0433\u0435\u043d\u0442\u0430. \u041a\u043e\u0433\u0434\u0430 LLM \u043d\u0430\u0443\u0447\u0430\u0442\u0441\u044f \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432 \u0434\u043b\u044f \u0434\u043e\u0441\u0442\u0438\u0436\u0435\u043d\u0438\u044f \u0446\u0435\u043b\u0438, \u043e\u043d\u0438 \u0441\u0442\u0430\u043d\u0443\u0442 \u0435\u0449\u0435 \u0431\u043e\u043b\u0435\u0435 \u043f\u043e\u043b\u0435\u0437\u043d\u044b\u043c\u0438 \u0434\u043b\u044f \u043d\u0430\u0441, \u0447\u0435\u043c \u0441\u0435\u0439\u0447\u0430\u0441.<\/p>\n<p>\u0411\u0443\u0434\u0443\u0449\u0435\u0435, \u0432 \u043a\u043e\u0442\u043e\u0440\u043e\u043c \u043f\u043e\u043c\u043e\u0449\u043d\u0438\u043a \u0441 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u044b\u043c \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u043e\u043c \u0431\u0443\u0434\u0435\u0442 \u0431\u0440\u043e\u043d\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0431\u0438\u043b\u0435\u0442\u044b \u043d\u0430 \u0441\u0430\u043c\u043e\u043b\u0435\u0442, \u043a\u043e\u043e\u0440\u0434\u0438\u043d\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0432\u0441\u0442\u0440\u0435\u0447\u0443 \u0438\u043b\u0438 \u0434\u0435\u043b\u0430\u0442\u044c \u043f\u043e\u043a\u0443\u043f\u043a\u0438 \u0437\u0430 \u0432\u0430\u0441, \u043a\u0430\u0436\u0435\u0442\u0441\u044f \u043d\u0435 \u0442\u0430\u043a\u0438\u043c \u0443\u0436 \u0434\u0430\u043b\u0435\u043a\u0438\u043c.<\/p>","protected":false},"excerpt":{"rendered":"<p>\u0418\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0438 \u0438\u0437 Meta \u0438 \u041a\u0430\u043b\u0438\u0444\u043e\u0440\u043d\u0438\u0439\u0441\u043a\u043e\u0433\u043e \u0443\u043d\u0438\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442\u0430 \u0432 \u0421\u0430\u043d-\u0414\u0438\u0435\u0433\u043e (UCSD) \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0430\u043b\u0438 ToolVerifier - \u043c\u0435\u0442\u043e\u0434, \u043a\u043e\u0442\u043e\u0440\u044b\u0439 \u0443\u043b\u0443\u0447\u0448\u0430\u0435\u0442 \u0442\u043e, \u043a\u0430\u043a LLM \u0432\u044b\u0437\u044b\u0432\u0430\u044e\u0442 \u0438 \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u0443\u044e\u0442 \u0441 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u044b\u043c\u0438 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043c\u0438. \u0414\u043b\u044f \u0442\u043e\u0433\u043e \u0447\u0442\u043e\u0431\u044b LLM \u0441\u0442\u0430\u043b\u0438 \u043f\u043e\u043b\u0435\u0437\u043d\u044b\u043c\u0438 \u043f\u043e\u043c\u043e\u0449\u043d\u0438\u043a\u0430\u043c\u0438 \u0438\u043b\u0438 \u0430\u0433\u0435\u043d\u0442\u0430\u043c\u0438 \u043e\u0431\u0449\u0435\u0433\u043e \u043d\u0430\u0437\u043d\u0430\u0447\u0435\u043d\u0438\u044f, \u0438\u0445 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e \u043d\u0430\u0443\u0447\u0438\u0442\u044c \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u044c \u0440\u0430\u0437\u043b\u0438\u0447\u043d\u044b\u0435 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u044b \u0438\u043b\u0438 API. \u0422\u043e\u043d\u043a\u0430\u044f \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0430 LLM \u043d\u0430 \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u043d\u0438\u0435 \u043a\u043e\u043d\u043a\u0440\u0435\u0442\u043d\u043e\u0433\u043e \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430 \u0434\u0430\u0435\u0442 \u0441\u0432\u043e\u0438 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u044b, \u043d\u043e \u043d\u0430\u0441\u0442\u043e\u044f\u0449\u0430\u044f \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u0430 \u0437\u0430\u043a\u043b\u044e\u0447\u0430\u0435\u0442\u0441\u044f \u0432 \u0442\u043e\u043c, \u0447\u0442\u043e\u0431\u044b LLM \u043c\u043e\u0433 \u0432\u0437\u0430\u0438\u043c\u043e\u0434\u0435\u0439\u0441\u0442\u0432\u043e\u0432\u0430\u0442\u044c \u0441 \u043d\u043e\u0432\u044b\u043c\u0438 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430\u043c\u0438 \u0431\u0435\u0437 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e\u0441\u0442\u0438 \u0442\u043e\u043d\u043a\u043e\u0439 \u043d\u0430\u0441\u0442\u0440\u043e\u0439\u043a\u0438 \u0438\u043b\u0438 \u0434\u0435\u043c\u043e\u043d\u0441\u0442\u0440\u0430\u0446\u0438\u0438 \u0432 \u043d\u0435\u0441\u043a\u043e\u043b\u044c\u043a\u0438\u0445 \u044d\u043a\u0437\u0435\u043c\u043f\u043b\u044f\u0440\u0430\u0445. \u041a\u043e\u0433\u0434\u0430 \u0434\u0432\u0430 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u0430 \u043e\u0447\u0435\u043d\u044c \u043f\u043e\u0445\u043e\u0436\u0438, \u0434\u043b\u044f LLM \u043c\u043e\u0436\u0435\u0442 \u0431\u044b\u0442\u044c \u043e\u0441\u043e\u0431\u0435\u043d\u043d\u043e \u0441\u043b\u043e\u0436\u043d\u043e \u0432\u044b\u0431\u0440\u0430\u0442\u044c \u043f\u0440\u0430\u0432\u0438\u043b\u044c\u043d\u044b\u0439 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442 \u0434\u043b\u044f \u0432\u044b\u043f\u043e\u043b\u043d\u0435\u043d\u0438\u044f \u0441\u0432\u043e\u0435\u0439 \u0437\u0430\u0434\u0430\u0447\u0438.<\/p>","protected":false},"author":6,"featured_media":10390,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[118,131],"class_list":["post-10380","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-llms","tag-meta"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Meta, UCSD introduce ToolVerifier to improve LLM tool calls | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/ru\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/\" \/>\n<meta property=\"og:locale\" content=\"ru_RU\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Meta, UCSD introduce ToolVerifier to improve LLM tool calls | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Researchers from Meta and the University of California San Diego (UCSD) developed ToolVerifier, a method that improves how LLMs call and interact with software tools. For LLMs to become useful as general assistants or agents, they need to be taught how to use various tools or APIs. Fine-tuning an LLM to use a specific tool does work, but the real challenge is for an LLM to interact with new tools without the need for fine-tuning or few-shot demonstrations. When two tools are very similar, it can be especially challenging for the LLM to choose the correct one to accomplish its\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/ru\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-28T10:18:11+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-tool-selection.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"449\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Eugene van der Watt\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"\u041d\u0430\u043f\u0438\u0441\u0430\u043d\u043e \u0430\u0432\u0442\u043e\u0440\u043e\u043c\" \/>\n\t<meta name=\"twitter:data1\" content=\"Eugene van der Watt\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u041f\u0440\u0438\u043c\u0435\u0440\u043d\u043e\u0435 \u0432\u0440\u0435\u043c\u044f \u0434\u043b\u044f \u0447\u0442\u0435\u043d\u0438\u044f\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 \u043c\u0438\u043d\u0443\u0442\u044b\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/\"},\"author\":{\"name\":\"Eugene van der Watt\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\"},\"headline\":\"Meta, UCSD introduce ToolVerifier to improve LLM tool calls\",\"datePublished\":\"2024-02-28T10:18:11+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/\"},\"wordCount\":488,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-tool-selection.jpg\",\"keywords\":[\"LLMS\",\"Meta\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"ru-RU\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/\",\"name\":\"Meta, UCSD introduce ToolVerifier to improve LLM tool calls | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-tool-selection.jpg\",\"datePublished\":\"2024-02-28T10:18:11+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/#breadcrumb\"},\"inLanguage\":\"ru-RU\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ru-RU\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-tool-selection.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/02\\\/AI-tool-selection.jpg\",\"width\":1000,\"height\":449},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/02\\\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Meta, UCSD introduce ToolVerifier to improve LLM tool calls\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ru-RU\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ru-RU\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/7ce525c6d0c79838b7cc7cde96993cfa\",\"name\":\"Eugene van der Watt\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ru-RU\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/07\\\/Eugine_Profile_Picture-96x96.png\",\"caption\":\"Eugene van der Watt\"},\"description\":\"Eugene comes from an electronic engineering background and loves all things tech. When he takes a break from consuming AI news you'll find him at the snooker table.\",\"sameAs\":[\"www.linkedin.com\\\/in\\\/eugene-van-der-watt-16828119\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/ru\\\/author\\\/eugene\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Meta, UCSD \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 ToolVerifier \u0434\u043b\u044f \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044f \u0432\u044b\u0437\u043e\u0432\u043e\u0432 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432 LLM | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/ru\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/","og_locale":"ru_RU","og_type":"article","og_title":"Meta, UCSD introduce ToolVerifier to improve LLM tool calls | DailyAI","og_description":"Researchers from Meta and the University of California San Diego (UCSD) developed ToolVerifier, a method that improves how LLMs call and interact with software tools. For LLMs to become useful as general assistants or agents, they need to be taught how to use various tools or APIs. Fine-tuning an LLM to use a specific tool does work, but the real challenge is for an LLM to interact with new tools without the need for fine-tuning or few-shot demonstrations. When two tools are very similar, it can be especially challenging for the LLM to choose the correct one to accomplish its","og_url":"https:\/\/dailyai.com\/ru\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/","og_site_name":"DailyAI","article_published_time":"2024-02-28T10:18:11+00:00","og_image":[{"width":1000,"height":449,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-tool-selection.jpg","type":"image\/jpeg"}],"author":"Eugene van der Watt","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"\u041d\u0430\u043f\u0438\u0441\u0430\u043d\u043e \u0430\u0432\u0442\u043e\u0440\u043e\u043c":"Eugene van der Watt","\u041f\u0440\u0438\u043c\u0435\u0440\u043d\u043e\u0435 \u0432\u0440\u0435\u043c\u044f \u0434\u043b\u044f \u0447\u0442\u0435\u043d\u0438\u044f":"3 \u043c\u0438\u043d\u0443\u0442\u044b"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/"},"author":{"name":"Eugene van der Watt","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa"},"headline":"Meta, UCSD introduce ToolVerifier to improve LLM tool calls","datePublished":"2024-02-28T10:18:11+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/"},"wordCount":488,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-tool-selection.jpg","keywords":["LLMS","Meta"],"articleSection":["Industry"],"inLanguage":"ru-RU"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/","url":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/","name":"Meta, UCSD \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u044e\u0442 ToolVerifier \u0434\u043b\u044f \u0443\u043b\u0443\u0447\u0448\u0435\u043d\u0438\u044f \u0432\u044b\u0437\u043e\u0432\u043e\u0432 \u0438\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442\u043e\u0432 LLM | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-tool-selection.jpg","datePublished":"2024-02-28T10:18:11+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/#breadcrumb"},"inLanguage":"ru-RU","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/"]}]},{"@type":"ImageObject","inLanguage":"ru-RU","@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-tool-selection.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/02\/AI-tool-selection.jpg","width":1000,"height":449},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/02\/meta-ucsd-introduce-toolverifier-to-improve-llm-tool-calls\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Meta, UCSD introduce ToolVerifier to improve LLM tool calls"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"\u0412\u0430\u0448\u0430 \u0435\u0436\u0435\u0434\u043d\u0435\u0432\u043d\u0430\u044f \u0434\u043e\u0437\u0430 \u043d\u043e\u0432\u043e\u0441\u0442\u0435\u0439 \u043e\u0431 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u043c \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0435","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ru-RU"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"ru-RU","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/7ce525c6d0c79838b7cc7cde96993cfa","name":"\u042e\u0434\u0436\u0438\u043d \u0432\u0430\u043d \u0434\u0435\u0440 \u0412\u0430\u0442\u0442","image":{"@type":"ImageObject","inLanguage":"ru-RU","@id":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/07\/Eugine_Profile_Picture-96x96.png","caption":"Eugene van der Watt"},"description":"\u042e\u0434\u0436\u0438\u043d - \u0432\u044b\u0445\u043e\u0434\u0435\u0446 \u0438\u0437 \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u043e\u0439 \u0438\u043d\u0436\u0435\u043d\u0435\u0440\u0438\u0438 \u0438 \u043e\u0431\u043e\u0436\u0430\u0435\u0442 \u0432\u0441\u0435, \u0447\u0442\u043e \u0441\u0432\u044f\u0437\u0430\u043d\u043e \u0441 \u0442\u0435\u0445\u043d\u0438\u043a\u043e\u0439. \u041a\u043e\u0433\u0434\u0430 \u043e\u043d \u043e\u0442\u0434\u044b\u0445\u0430\u0435\u0442 \u043e\u0442 \u0447\u0442\u0435\u043d\u0438\u044f \u043d\u043e\u0432\u043e\u0441\u0442\u0435\u0439 \u043e\u0431 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u043c \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0435, \u0432\u044b \u043c\u043e\u0436\u0435\u0442\u0435 \u043d\u0430\u0439\u0442\u0438 \u0435\u0433\u043e \u0437\u0430 \u0441\u0442\u043e\u043b\u043e\u043c \u0434\u043b\u044f \u0438\u0433\u0440\u044b \u0432 \u0441\u043d\u0443\u043a\u0435\u0440.","sameAs":["www.linkedin.com\/in\/eugene-van-der-watt-16828119"],"url":"https:\/\/dailyai.com\/ru\/author\/eugene\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/posts\/10380","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/comments?post=10380"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/posts\/10380\/revisions"}],"predecessor-version":[{"id":10392,"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/posts\/10380\/revisions\/10392"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/media\/10390"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/media?parent=10380"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/categories?post=10380"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/ru\/wp-json\/wp\/v2\/tags?post=10380"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}