{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:23:42Z","timestamp":1793132622101,"version":"4.5.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Research Foundation of Korea","award":["RS-2025-16902996"],"award-info":[{"award-number":["RS-2025-16902996"]}],"id":[{"id":"https:\/\/ror.org\/013aysd81","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Korea Government"},{"name":"Ministry of Science and ICT","id":[{"id":"https:\/\/ror.org\/01wpjm123","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation","id":[{"id":"https:\/\/ror.org\/01g0hqq23","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Artificial Intelligence Graduate School Program"},{"name":"Gwangju Institute of Science and Technology","award":["2019-0-01842"],"award-info":[{"award-number":["2019-0-01842"]}],"id":[{"id":"https:\/\/ror.org\/024kbgz78","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Korea Government"},{"name":"Ministry of Science and ICT","id":[{"id":"https:\/\/ror.org\/01wpjm123","id-type":"ROR","asserted-by":"crossref"}]},{"name":"GIST through the GIST-International Research Experience Fellowship program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tg.2026.3695197","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:54:29Z","timestamp":1779306869000},"page":"529-542","source":"Crossref","is-referenced-by-count":2,"title":["PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9409-9253","authenticated-orcid":false,"given":"In-Chang","family":"Baek","sequence":"first","affiliation":[{"name":"Gwangju Institute of Science Technology","place":["Gwangju, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung-Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Gwangju Institute of Science Technology","place":["Gwangju, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3783-9486","authenticated-orcid":false,"given":"Sam","family":"Earle","sequence":"additional","affiliation":[{"name":"New York University","place":["New York, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1807-7826","authenticated-orcid":false,"given":"Zehua","family":"Jiang","sequence":"additional","affiliation":[{"name":"New York University","place":["New York, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4071-2673","authenticated-orcid":false,"given":"Jin-Ha","family":"Noh","sequence":"additional","affiliation":[{"name":"Gwangju Institute of Science Technology","place":["Gwangju, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3128-4598","authenticated-orcid":false,"given":"Julian","family":"Togelius","sequence":"additional","affiliation":[{"name":"New York University","place":["New York, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7732-0817","authenticated-orcid":false,"given":"Kyung-Joong","family":"Kim","sequence":"additional","affiliation":[{"name":"Gwangju Institute of Science Technology","place":["Gwangju, South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05383-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7416"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619159"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3555858.3563273"},{"key":"ref5","first-page":"26516","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2024","author":"Ma","year":"2024"},{"key":"ref6","article-title":"Learning reward for physical skills using large language model","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng","year":"2023"},{"key":"ref7","first-page":"374","article-title":"Language to rewards for robotic skill synthesis","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Yu","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01554"},{"key":"ref9","article-title":"Online intrinsic rewards for decision making agents from large language model feedback","volume-title":"Proc. Reinforcement Learn. Conf.","author":"Zheng","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645619"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645598"},{"key":"ref12","first-page":"2601","article-title":"Where do rewards come from","volume-title":"Proc. Int. Symp. AI-Inspired Biol.","author":"Lewis","year":"2010"},{"key":"ref13","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Ahn","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"ref15","article-title":"Self-refined large language model as automated reward function designer for deep reinforcement learning in robotics","author":"Song","year":"2023"},{"key":"ref16","article-title":"Text2Reward: Automated dense reward function generation for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2011.2148116"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3175795"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CoG64752.2025.11114105"},{"key":"ref20","article-title":"Multi-objective instruction-aware representation learning in procedural content generation RL","author":"Kim","year":"2026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2026.3713793"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2024.3399536"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3335399"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645633"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref27","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref31","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref32","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2361"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3582437.3587211"},{"key":"ref35","article-title":"A text-to-game engine for UGC-based role-playing games","author":"Zhang","year":"2024"},{"key":"ref36","article-title":"Word2World: Generating stories and worlds through large language models","author":"Nasir","year":"2024"},{"key":"ref37","article-title":"GPT-4o system card","author":"Hurst","year":"2024"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1197"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/beheco\/ark016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2846639"},{"key":"ref42","article-title":"JAX: Composable transformations of python NumPy programs","author":"Bradbury","year":"2018"},{"key":"ref43","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11693993\/11527037.pdf?arnumber=11527037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:11:22Z","timestamp":1790269882000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11527037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2026.3695197","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}