{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T19:44:06Z","timestamp":1782243846095,"version":"3.54.5"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Online question-and-answer (Q&amp;amp;A) systems based on the Large Language Model (LLM) have progressively diverged from recreational to professional use. However, beginners in programming often struggle to correct code errors independently, limiting their learning efficiency. This paper proposed a Multi-Agent framework with environmentally reinforcement learning (E-RL) for code correction called Code Learning (Co-Learning) community, assisting beginners to correct code errors independently. It evaluates the performance of multiple LLMs from an original dataset with 702 error codes, uses it as a reward or punishment criterion for E-RL; Analyzes input error codes by the current agent; selects the appropriate LLM-based agent to achieve optimal error correction accuracy and reduce correction time. Experiment results showed that 3% improvement in Precision score and 15% improvement in time cost as compared with no E-RL method respectively. The results indicate that integrating E-RL with a multi-agent selection strategy can effectively enhance both the accuracy and efficiency of LLM-based code correction systems, making them more practical for educational and professional programming support scenarios.<\/jats:p>","DOI":"10.3389\/frai.2025.1431003","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T08:34:44Z","timestamp":1747298084000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Co-Learning: code learning for multi-agent reinforcement collaborative framework with conversational natural language interfaces"],"prefix":"10.3389","volume":"8","author":[{"given":"Jiapeng","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajing","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,15]]},"reference":[{"key":"ref1","author":"Austin","year":"2021"},{"key":"ref2","author":"Barrault","year":"2023"},{"key":"ref3","author":"Bellifemine","year":"2001"},{"key":"ref4","first-page":"3","article-title":"An introduction to software agents","volume":"4","author":"Bradshaw","year":"1997","journal-title":"Software Agents"},{"key":"ref5","author":"Chen","year":"2023"},{"key":"ref6","author":"Fang","year":"2024"},{"key":"ref7","author":"Ganguli","year":"2023"},{"key":"ref8","unstructured":"2023"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: a survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","article-title":"Deep reinforcement learning for autonomous driving: a survey","volume":"23","author":"Kiran","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref11","volume-title":"Fuzzy-neuro approach to agent applications: From the AI perspective to modern ontology","author":"Lee","year":"2005"},{"key":"ref12","author":"Lee","year":"2001"},{"key":"ref13","author":"Li","year":"2023"},{"key":"ref14","author":"Lillicrap","year":"2015"},{"key":"ref9001","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"36","author":"Madaan","year":"2024","journal-title":"Adv Neural Inf Process Syst."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e12012","DOI":"10.1002\/2050-7038.12012","article-title":"Python-based multi-agent platform for application on power grids","volume":"29","author":"Melo","year":"2019","journal-title":"Int. Trans. Electr. Energy Syst."},{"key":"ref16","author":"Nair","year":"2023"},{"key":"ref17","author":"Nijkamp","year":"2022"},{"key":"ref18","year":"2023"},{"key":"ref19","author":"Schick","year":"2020"},{"key":"ref20","author":"Shinn","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"ref22","author":"Sumers","year":"2023"},{"key":"ref23","author":"Sun","year":"2021"},{"key":"ref24","author":"Touvron","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11704-024-40231-1","article-title":"A survey on large language model based autonomous agents","volume":"18","author":"Wang","year":"2024","journal-title":"Front. Comp. Sci."},{"key":"ref26","author":"Xi","year":"2023"},{"key":"ref27","author":"Zhang","year":"2023"},{"key":"ref28","author":"Zhou","year":"2023"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1431003\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T08:34:46Z","timestamp":1747298086000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1431003\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"references-count":29,"alternative-id":["10.3389\/frai.2025.1431003"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1431003","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,15]]},"article-number":"1431003"}}