{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T18:15:13Z","timestamp":1779387313088,"version":"3.53.1"},"reference-count":42,"publisher":"Institution of Engineering and Technology (IET)","issue":"2","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62501094"],"award-info":[{"award-number":["62501094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>As a government\u2010regulated public service, traffic signal control (TSC) requires reliable and transparent decision\u2010making. However, existing deep reinforcement learning (DRL) methods, despite improvements in control accuracy, still lack explainability and generalisation, severely limiting their applicability in real\u2010world environments. To address the challenges above, this paper proposes GenEx\u2010TSC, a generalisable and explainable TSC method that integrates deep reinforcement learning with large language models (LLMs). First, starting from vehicle\u2010level states, we train a DRL agent incorporating intersection physical heterogeneity and neighbourhood information, which lays the evaluation foundation for constructing a high\u2010quality LLM dataset. Subsequently, the LLM agent is optimised through a two\u2010stage training mechanism. In the distillation stage, a lightweight LLM agent is trained using the reasoning trajectories of a larger\u2010scale LLM agent, inheriting its semantic understanding and decision\u2010generation capabilities and in the alignment stage, the DRL evaluation network is employed to calibrate the outputs of the distilled LLM agent, ensuring that the generated cycle\u2010level signal timing strategies are both efficient and interpretable. We synthesise 10 intersection networks with different physical attributes in SUMO and set traffic flows of varying scales. Experimental results across diverse traffic environments demonstrate that the proposed GenEx\u2010TSC exhibits clear advantages over traditional methods, mainstream DRL methods and LLM baselines in terms of control accuracy, generalisation and explainability.<\/jats:p>","DOI":"10.1049\/cit2.70113","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T14:24:01Z","timestamp":1772979841000},"page":"483-497","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Generalisable and Explainable Traffic Signal Control via Deep Reinforcement Learning and Large Language Models"],"prefix":"10.1049","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3151-367X","authenticated-orcid":false,"given":"Hao","family":"Huang","sequence":"first","affiliation":[{"name":"Chongqing Key Laboratory of Mobile Communications Technology, School of Communications and Information Engineering Chongqing University of Posts and Telecommunications  Chongqing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"He","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Mobile Communications Technology, School of Communications and Information Engineering Chongqing University of Posts and Telecommunications  Chongqing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qilie","family":"Liu","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Mobile Communications Technology, School of Communications and Information Engineering Chongqing University of Posts and Telecommunications  Chongqing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Liu","sequence":"additional","affiliation":[{"name":"Chongqing Key Laboratory of Mobile Communications Technology, School of Communications and Information Engineering Chongqing University of Posts and Telecommunications  Chongqing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anwar P. P.","family":"Abdul Majeed","sequence":"additional","affiliation":[{"name":"Sunway University  Bandar Sunway Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1846-2580","authenticated-orcid":false,"given":"Xiangguang","family":"Dai","sequence":"additional","affiliation":[{"name":"Chongqing Three Gorges University  Chongqing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Fang","sequence":"additional","affiliation":[{"name":"Chongqing Three Gorges University  Chongqing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhaotong University  Zhaotong China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2024.173896"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbspro.2013.08.071"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.treng.2024.100252"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108100"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/jas.2016.7508798"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3107258"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2021.3067057"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108304"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3536541"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3556931"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3087228"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104663"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.16511\/j.cnki.qhdxxb.2021.26.026"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102682"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3526223"},{"key":"e_1_2_9_17_1","article-title":"Inductive Meta\u2010Deep Reinforcement Learning for Traffic Signal Control Considering Heterogeneity in Traffic Environments","author":"Huang H.","year":"2025","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17251"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671595"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12924"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"e_1_2_9_22_1","first-page":"21107","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Gu Y.","year":"2024"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2022.3225362"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14177455"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27758"},{"key":"e_1_2_9_27_1","unstructured":"M.Wang A.Pang Y.Kan M.\u2010O.Pun C. S.ChenandB.Huang \u201cLlm\u2010Assisted Light: Leveraging Large Language Model Capabilities for Human\u2010Mimetic Traffic Signal Control in Complex Urban Environments \u201d preprint arXiv:2403.08337 (2024)."},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3498735"},{"key":"e_1_2_9_29_1","unstructured":"A.Pang M.Wang M.\u2010O.Pun C. S.ChenandX.Xiong \u201cIllm\u2010tsc: Integration Reinforcement Learning and Large Language Model for Traffic Signal Control Policy Improvement \u201d preprint arXiv:2407.06025 (2024)."},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709379"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2024.3359282"},{"key":"e_1_2_9_32_1","first-page":"1587","volume-title":"International Conference on Machine Learning","author":"Fujimoto S.","year":"2018"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"e_1_2_9_34_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Velickovic P.","year":"2018"},{"key":"e_1_2_9_35_1","first-page":"18345","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Ji B.","year":"2024"},{"key":"e_1_2_9_36_1","first-page":"8361","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"\u0160trupl M.","year":"2022"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1400713.1400740"},{"key":"e_1_2_9_39_1","unstructured":"P.Koonce \u201c\u2018Traffic Signal Timing Manual \u2019 United States \u201d Federal Highway Administration Tech. Rep. (2008)."},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.08.014"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"e_1_2_9_42_1","unstructured":"A.Liu B.Feng B.Xue et\u00a0al. \u201cDeepseek\u2010v3 Technical Report \u201d preprint arXiv:2412.19437 (2024)."},{"key":"e_1_2_9_43_1","first-page":"3","volume-title":"International Conference on Learning Representations","author":"Hu E. J.","year":"2022"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70113","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.70113","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70113","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:56:08Z","timestamp":1779386168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.70113"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1049\/cit2.70113"],"URL":"https:\/\/doi.org\/10.1049\/cit2.70113","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,5]]},"assertion":[{"value":"2025-10-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}