{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T18:28:45Z","timestamp":1769020125398,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"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":[[2025,7,8]]},"DOI":"10.23919\/acc63710.2025.11107729","type":"proceedings-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:51Z","timestamp":1755800271000},"page":"583-590","source":"Crossref","is-referenced-by-count":2,"title":["Synthesizing Interpretable Control Policies through Large Language Model Guided Search"],"prefix":"10.23919","author":[{"given":"Carlo","family":"Bosio","sequence":"first","affiliation":[{"name":"University of California,High Performance Robotics Laboratory,Berkeley"}]},{"given":"Mark W.","family":"Mueller","sequence":"additional","affiliation":[{"name":"University of California,High Performance Robotics Laboratory,Berkeley"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06924-6"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref3","article-title":"Incoder: A generative model for code infilling and synthesis","author":"Fried","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1108\/ws.2000.07949fab.004"},{"key":"ref5","article-title":"Starcoder 2 and the stack v2: The next generation","author":"Lozhkov","year":"2024"},{"key":"ref6","article-title":"Program synthesis with large language models","author":"Austin","year":"2021"},{"key":"ref7","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref8","first-page":"15 476","article-title":"Star: Bootstrapping reasoning with reasoning","volume":"35","author":"Zelikman","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Language models can teach themselves to program better","author":"Haluptzok","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-3814-8_11"},{"key":"ref11","article-title":"An example of evolutionary computation+ large language model beating human: Design of efficient guided local search","author":"Liu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.07.014"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898719376","volume-title":"L 1 adaptive control theory: Guaranteed robustness with fast adaptation","author":"Hovakimyan","year":"2010"},{"key":"ref14","volume-title":"Adaptive control: stability, convergence and robustness","author":"Sastry","year":"2011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1636313"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref17","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018","journal-title":"A Bradford Book"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref20","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on robot learning","author":"Kalashnikov"},{"key":"ref21","article-title":"Towards a rigorous science of interpretable machine learning","author":"Doshi-Velez","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06543-w"},{"key":"ref23","article-title":"Interpretable reinforcement learning for robotics and continuous control","author":"Paleja","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3208277"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2277"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2970626"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/21-SS133"},{"key":"ref28","volume-title":"Reinforcement learning and optimal control","volume":"1","author":"Bertsekas","year":"2019"},{"issue":"2","key":"ref29","first-page":"141","article-title":"A survey of parallel genetic algorithms","volume":"10","author":"Cant\u00fa-Paz","year":"1998","journal-title":"Calculateurs paralleles, reseaux et systems repartis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref31","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref33","article-title":"Llm and simulation as bilevel optimizers: A new paradigm to advance physical scientific discovery","author":"Ma","year":"2024"}],"event":{"name":"2025 American Control Conference (ACC)","location":"Denver, CO, USA","start":{"date-parts":[[2025,7,8]]},"end":{"date-parts":[[2025,7,10]]}},"container-title":["2025 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11107441\/11107442\/11107729.pdf?arnumber=11107729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:24:43Z","timestamp":1755840283000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107729\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/acc63710.2025.11107729","relation":{},"subject":[],"published":{"date-parts":[[2025,7,8]]}}}