{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:15:36Z","timestamp":1774721736248,"version":"3.50.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208959","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":13,"title":["FALCON: Feedback-driven Adaptive Long\/short-term memory reinforced Coding OptimizatioN"],"prefix":"10.1109","author":[{"given":"Zeyuan","family":"Li","sequence":"first","affiliation":[{"name":"South China Normal University,School of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangfan","family":"He","sequence":"additional","affiliation":[{"name":"University of Minnesota - Twin Cities"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lewei","family":"He","sequence":"additional","affiliation":[{"name":"South China Normal University,School of Software"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhui","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Lei","sequence":"additional","affiliation":[{"name":"University of Connecticut"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Li","sequence":"additional","affiliation":[{"name":"AIGCode Inc.,AI Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuwu","family":"Chen","sequence":"additional","affiliation":[{"name":"AIGCode Inc.,AI Center"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.411"},{"key":"ref2","article-title":"Code llama: Open foundation models for code","author":"Roziere","year":"2023"},{"key":"ref3","article-title":"Deepseek-coder: When the large language model meets programming\u2013the rise of code intelligence","author":"Guo","year":"2024"},{"key":"ref4","article-title":"A survey on large language models for code generation","author":"Jiang","year":"2024"},{"key":"ref5","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref6","first-page":"21314","article-title":"Coderl: Mastering code generation through pretrained models and deep reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Le","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.2"},{"key":"ref8","article-title":"RLTF: Reinforcement learning from unit test feedback","author":"Liu","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599790"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.716"},{"key":"ref14","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Fujimoto"},{"key":"ref15","article-title":"Execution-based code generation using deep reinforcement learning","author":"Shojaee","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.251"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-4001-0_24"},{"key":"ref18","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.5119629","article-title":"Enhancing intent understanding for ambiguous prompt: A human-machine co-adaption strategy","volume-title":"ICML 2024 Workshop on Models of Human Feedback for AI Alignment","author":"He"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208959.pdf?arnumber=11208959","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:53:35Z","timestamp":1761890015000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208959\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208959","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}