{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T05:12:16Z","timestamp":1788844336981,"version":"build-2803163510"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3728498","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T19:08:46Z","timestamp":1788289726000},"page":"135822-135836","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Auditory Reasoning in Large Audio\u2013Language Models Via Supervised Fine-Tuning and Reinforcement Learning With Verifiable Rewards"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3115-4065","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"first","affiliation":[{"name":"Procuratorial Affairs Center of Yantai Municipal People\u2019s Procuratorate","place":["Yantai, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengyan","family":"Hao","sequence":"additional","affiliation":[{"name":"Procuratorial Affairs Center of Shandong Provincial People\u2019s Procuratorate","place":["Jinan, Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"OpenAI o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv:2412.16720"},{"key":"ref2","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref3","article-title":"Kimi k1.5: Scaling reinforcement learning with LLMs","author":"Team","year":"2025","journal-title":"arXiv:2501.12599"},{"key":"ref4","article-title":"Marco-o1: Towards open reasoning models for open-ended solutions","author":"Zhao","year":"2024","journal-title":"arXiv:2411.14405"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"ref6","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref7","article-title":"O1-coder: An o1 replication for coding","author":"Zhang","year":"2024","journal-title":"arXiv:2412.00154"},{"key":"ref8","article-title":"From explicit CoT to implicit CoT: Learning to internalize CoT step by step","author":"Deng","year":"2024","journal-title":"arXiv:2405.14838"},{"key":"ref9","article-title":"Qwen2.5-coder technical report","volume-title":"arXiv:2409.12186","author":"Hui","year":"2024"},{"key":"ref10","article-title":"Qwen2.5-math technical report: Toward mathematical expert model via self-improvement","volume-title":"arXiv:2409.12122","author":"Yang","year":"2024"},{"key":"ref11","article-title":"Visual CoT: Unleashing chain-of-thought reasoning in multi-modal language models","author":"Shao","year":"2024","journal-title":"arXiv:2403.16999"},{"key":"ref12","article-title":"Improve vision language model chain-of-thought reasoning","author":"Zhang","year":"2024","journal-title":"arXiv:2410.16198"},{"key":"ref13","article-title":"MAmmoTH-VL: Eliciting multimodal reasoning with instruction tuning at scale","author":"Guo","year":"2024","journal-title":"arXiv:2412.05237"},{"key":"ref14","article-title":"Generalizable chain-of-thought prompting in mixed-task scenarios with large language models","author":"Zou","year":"2023","journal-title":"arXiv:2310.06692"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06426-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687885"},{"key":"ref17","first-page":"1","article-title":"Multimodal sentiment analysis model based on alignment prompt learning","volume-title":"Proc. Chin. Conf. Pattern Recognit. Comput. Vis. (PRCV)","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tifs.2018.11.017"},{"key":"ref19","article-title":"Image-of-thought prompting for visual reasoning refinement in multimodal large language models","author":"Zhou","year":"2024","journal-title":"arXiv:2405.13872"},{"key":"ref20","article-title":"Enhancing temporal understanding in audio question answering for large audio language models","author":"Sridhar","year":"2024","journal-title":"arXiv:2409.06223"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2252"},{"key":"ref22","first-page":"1","article-title":"MMAU: A massive multi-task audio understanding and reasoning benchmark","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sakshi"},{"key":"ref23","first-page":"25125","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/085713-1396"},{"key":"ref25","article-title":"SALMONN: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv:2310.13289"},{"key":"ref26","article-title":"Qwen2-audio technical report","volume-title":"arXiv:2407.10759","author":"Chu","year":"2024"},{"key":"ref27","article-title":"Kimi-audio technical report","volume-title":"arXiv:2504.18425","author":"Chu","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3622978"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096230"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2026.3682068"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU65441.2025.11434628"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref35","volume-title":"R1-V: Reinforcing Super Generalization Ability in Vision-Language Models With Less Than $3","author":"Chen","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"ref37","article-title":"Audio flamingo 2: An audio-language model with long-audio understanding and expert reasoning abilities","author":"Ghosh","year":"2025","journal-title":"arXiv:2503.03983"},{"key":"ref38","article-title":"DeepSeekMath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"arXiv:2402.03300"},{"key":"ref39","article-title":"Qwen2.5-omni technical report","volume-title":"arXiv:2503.20215","author":"Ghosh","year":"2025"},{"key":"ref40","article-title":"Expanding on EnCLAP with auxiliary retrieval model for automated audio captioning","author":"Kim","year":"2024"},{"key":"ref41","article-title":"EnCLAP++: Analyzing the EnCLAP framework for optimizing automated audio captioning performance","author":"Kim","year":"2024","journal-title":"arXiv:2409.01201"},{"key":"ref42","article-title":"SJTU-THU automated audio captioning system for DCASE 2024","author":"Chen","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889071"},{"key":"ref44","article-title":"Leveraging CED encoder and large language models for automated audio captioning","author":"Liu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-65"},{"key":"ref46","article-title":"All roads lead to likelihood: The value of reinforcement learning in fine-tuning","author":"Swamy","year":"2025","journal-title":"arXiv:2503.01067"},{"key":"ref47","volume-title":"Learning to Reason With LLMs","year":"2024"},{"key":"ref48","article-title":"R1-zero\u2019s \u2018Aha moment\u2019 in visual reasoning on a 2B non-SFT model","author":"Zhou","year":"2025","journal-title":"arXiv:2503.05132"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/e25101421"},{"key":"ref51","article-title":"Audio-reasoner: Improving reasoning capability in large audio language models","author":"Xie","year":"2025","journal-title":"arXiv:2503.02318"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447795"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-295"},{"key":"ref54","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref55","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890259"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11672758.pdf?arnumber=11672758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T04:55:15Z","timestamp":1788843315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11672758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3728498","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}