{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:38:25Z","timestamp":1770917905094,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Large language models (LLMs) have garnered increasing attention owing to their powerful comprehension and generation capabilities. Generally, larger LLMs (L-LLMs) that require paid interfaces exhibit significantly superior performance compared to smaller LLMs (S-LLMs) that can be deployed on a variety of devices. Knowledge distillation (KD) aims to empower S-LLMs with the capabilities of L-LLMs, while S-LLMs merely mimic the outputs of L-LLMs, failing to get the powerful decision-making capability for new situations. Consequently, S-LLMs are helpless when it comes to continuous decision-making tasks that require logical reasoning. To tackle the identified challenges, we propose a novel framework called Logic Distillation (LD). Initially, LD employs L-LLMs to instantiate complex instructions into discrete functions and illustrates their usage to establish a function base. Subsequently, LD fine-tunes S-LLMs based on the function base to learn the logic employed by L-LLMs in decision-making. During testing, S-LLMs will yield decision-making outcomes, function by function, based on current states. Experiments demonstrate that with the assistance of LD, S-LLMs can achieve outstanding results in continuous decision-making tasks, comparable to, or even surpassing, those of L-LLMs. The code and data for the proposed method are provided for research purposes https:\/\/github.com\/Anfeather\/Logic-Distillation.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/816","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"7338-7346","source":"Crossref","is-referenced-by-count":1,"title":["Logic Distillation: Learning from Code Function by Function for Decision-making Tasks"],"prefix":"10.24963","author":[{"given":"Dong","family":"Chen","sequence":"first","affiliation":[{"name":"Zhengzhou University"},{"name":"Engineering Research Center of Intelligent Swarm Systems, Ministry of Education"},{"name":"National Supercomputing Center In Zhengzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shilin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhengzhou University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Gao","sequence":"additional","affiliation":[{"name":"Zhengzhou University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qidong","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhengzhou University"},{"name":"The School of Computer and Artificial Intelligence of Zhengzhou University"},{"name":"Engineering Research Center of Intelligent Swarm Systems, Ministry of Education"},{"name":"National Supercomputing Center In Zhengzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhengzhou University"},{"name":"Engineering Research Center of Intelligent Swarm Systems, Ministry of Education"},{"name":"National Supercomputing Center In Zhengzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2025","number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2025,8,16]]},"end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:35:12Z","timestamp":1758627312000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/816"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/816","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}