{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:28Z","timestamp":1786120828329,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research Grants Council of the Hong Kong Special Administrative Region, China","award":["T45-401\/22-N"],"award-info":[{"award-number":["T45-401\/22-N"]}]},{"name":"Young Scientists Fund (C Class) of the National Natural Science Foundation of China","award":["62506154"],"award-info":[{"award-number":["62506154"]}]},{"name":"Fundamental Research Funds for the Central Universities and Nanjing University International Collaboration Initiative","award":["020214380129"],"award-info":[{"award-number":["020214380129"]}]},{"name":"National Natural Science Foundation of China","award":["B26023"],"award-info":[{"award-number":["B26023"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818895","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"10520-10531","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The Forgetting-Learning Trade-off: Making Reinforcement Learning Work for Protein Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8104-1845","authenticated-orcid":false,"given":"Hanqun","family":"Cao","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5968-4247","authenticated-orcid":false,"given":"Hongrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9900-7039","authenticated-orcid":false,"given":"Junde","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0222-6391","authenticated-orcid":false,"given":"Zhou","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology at Nanjing University, School of Computer Science, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6783-0766","authenticated-orcid":false,"given":"Lingdong","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Environmental Sciences and Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8317-5847","authenticated-orcid":false,"given":"Minghao","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9383-5186","authenticated-orcid":false,"given":"Ge","family":"Liu","sequence":"additional","affiliation":[{"name":"Siebel School of Computing and Data Science, University of Illinois at Urbana-Champaign, Champaign, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7111-4839","authenticated-orcid":false,"given":"Jinbo","family":"Xu","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute at Chicago, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2499-4006","authenticated-orcid":false,"given":"Wu-Jun","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology at Nanjing University, School of Computer Science, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9114-8347","authenticated-orcid":false,"given":"Jinren","family":"Ni","sequence":"additional","affiliation":[{"name":"College of Environmental Sciences and Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2005-5629","authenticated-orcid":false,"given":"Cesar","family":"de la Fuente-Nunez","sequence":"additional","affiliation":[{"name":"Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5574-2541","authenticated-orcid":false,"given":"Tianfan","family":"Fu","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology at Nanjing University, School of Computer Science, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8113-9367","authenticated-orcid":false,"given":"Shuting","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3055-5034","authenticated-orcid":false,"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7240-3915","authenticated-orcid":false,"given":"Fang","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Science Department, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Functional alignment of protein language models via reinforcement learning. bioRxiv","author":"Blalock Nathaniel","year":"2025","unstructured":"Nathaniel Blalock, Srinath Seshadri, Agrim Babbar, Sarah A Fahlberg, Ameya Kulkarni, and Philip A Romero. 2025. Functional alignment of protein language models via reinforcement learning. bioRxiv (2025), 2025-05."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac020"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1101\/2025.09.23.678086"},{"key":"e_1_3_2_1_4_1","volume-title":"Pheng Ann Heng, and Pranam Chatterjee","author":"Cao Hanqun","year":"2026","unstructured":"Hanqun Cao, Aastha Pal, Sophia Tang, Yinuo Zhang, Jingjie Zhang, Pheng Ann Heng, and Pranam Chatterjee. 2026. TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation. arXiv preprint arXiv:2605.09810 (2026)."},{"key":"e_1_3_2_1_5_1","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=AHjspi4R22","author":"Cao Hanqun","year":"2025","unstructured":"Hanqun Cao, Haosen Shi, Chenyu Wang, Sinno Jialin Pan, and Pheng-Ann Heng. 2025b. GLID$textasciicircum2$E: A Gradient-Free Lightweight Fine-tune Approach for Discrete Biological Sequence Design. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=AHjspi4R22"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-29119-7_11"},{"key":"e_1_3_2_1_7_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv:2110.14168 [cs.LG] https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_1_8_1","volume-title":"V13, 1","author":"Ferruz Noelia","year":"2022","unstructured":"Noelia Ferruz, Steffen Schmidt, and Birte H\u00f6cker. 2022. ProtGPT2 is a deep unsupervised language model for protein design. Nature communications, V13, 1 (2022), 4348."},{"key":"e_1_3_2_1_9_1","volume-title":"Deep reinforcement learning for modelling protein complexes. arXiv preprint arXiv:2405.02299","author":"Gao Ziqi","year":"2024","unstructured":"Ziqi Gao, Tao Feng, Jiaxuan You, Chenyi Zi, Yan Zhou, Chen Zhang, and Jia Li. 2024. Deep reinforcement learning for modelling protein complexes. arXiv preprint arXiv:2405.02299 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.ads0018"},{"key":"e_1_3_2_1_12_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_13_1","volume-title":"HighPlay: Cyclic Peptide Sequence Design Based on Reinforcement Learning and Protein Structure Prediction. Journal of Medicinal Chemistry","author":"Lin Huitian","year":"2025","unstructured":"Huitian Lin, Cheng Zhu, Tianfeng Shang, Ning Zhu, Kang Lin, Chengyun Zhang, Xiang Shao, Xudong Wang, and Hongliang Duan. 2025. HighPlay: Cyclic Peptide Sequence Design Based on Reinforcement Learning and Protein Structure Prediction. Journal of Medicinal Chemistry (2025)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btaf446"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Isaac D. Lutz Shunzhi Wang Christoffer Norn Alexis Courbet Andrew J. Borst Yan Ting Zhao Annie Dosey Longxing Cao Jinwei Xu Elizabeth M. Leaf Catherine Treichel Patrisia Litvicov Zhe Li Alexander D. Goodson Paula Rivera-S\u00e1nchez Ana-Maria Bratovianu Minkyung Baek Neil P. King Hannele Ruohola-Baker and David Baker. 2023. Top-down design of protein architectures with reinforcement learning. Science V380 6642 (2023) 266-273. arXiv:https:\/\/www.science.org\/doi\/pdf\/10.1126\/science.adf6591 doi:10.1126\/science.adf6591","DOI":"10.1126\/science.adf6591"},{"key":"e_1_3_2_1_17_1","volume-title":"V14, 11","author":"Nijkamp Erik","year":"2023","unstructured":"Erik Nijkamp, Jeffrey A Ruffolo, Eli N Weinstein, Nikhil Naik, and Ali Madani. 2023. Progen2: exploring the boundaries of protein language models. Cell systems, V14, 11 (2023), 968-978."},{"key":"e_1_3_2_1_18_1","volume-title":"V36","author":"Ouyang-Zhang Jeffrey","year":"2023","unstructured":"Jeffrey Ouyang-Zhang, Daniel Diaz, Adam Klivans, and Philipp Kr\u00e4henb\u00fchl. 2023. Predicting a protein's stability under a million mutations. Advances in Neural Information Processing Systems, V36 (2023), 76229-76247."},{"key":"e_1_3_2_1_19_1","volume-title":"V49, D1","author":"Pirtskhalava Malak","year":"2021","unstructured":"Malak Pirtskhalava, Anthony A Amstrong, Maia Grigolava, Mindia Chubinidze, Evgenia Alimbarashvili, Boris Vishnepolsky, Andrei Gabrielian, Alex Rosenthal, Darrell E Hurt, and Michael Tartakovsky. 2021. DBAASP v3: database of antimicrobial\/cytotoxic activity and structure of peptides as a resource for development of new therapeutics. Nucleic acids research, V49, D1 (2021), D288-D297."},{"key":"e_1_3_2_1_20_1","volume-title":"V347, 6222","author":"Podgornaia Anna I","year":"2015","unstructured":"Anna I Podgornaia and Michael T Laub. 2015. Pervasive degeneracy and epistasis in a protein-protein interface. Science, V347, 6222 (2015), 673-677."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1101\/2024.04.17.589642"},{"key":"e_1_3_2_1_22_1","volume-title":"V36","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems, V36 (2023), 53728-53741."},{"key":"e_1_3_2_1_23_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_24_1","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. arXiv:2402.03300 [cs.CL] https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_3_2_1_25_1","volume-title":"V50, D1","author":"Shi Guobang","year":"2022","unstructured":"Guobang Shi, Xinyue Kang, Fanyi Dong, Yanchao Liu, Ning Zhu, Yuxuan Hu, Hanmei Xu, Xingzhen Lao, and Heng Zheng. 2022. DRAMP 3.0: an enhanced comprehensive data repository of antimicrobial peptides. Nucleic acids research, V50, D1 (2022), D488-D496."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa1079"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/pro.2829"},{"key":"e_1_3_2_1_28_1","volume-title":"V35, 11","author":"Steinegger Martin","year":"2017","unstructured":"Martin Steinegger and Johannes S\u00f6ding. 2017. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nature biotechnology, V35, 11 (2017), 1026-1028."},{"key":"e_1_3_2_1_29_1","volume-title":"SaProt: Protein Language Modeling with Structure-aware Vocabulary. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6MRm3G4NiU","author":"Su Jin","year":"2024","unstructured":"Jin Su, Chenchen Han, Yuyang Zhou, Junjie Shan, Xibin Zhou, and Fajie Yuan. 2024. SaProt: Protein Language Modeling with Structure-aware Vocabulary. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6MRm3G4NiU"},{"key":"e_1_3_2_1_30_1","volume-title":"PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion. In International Conference on Machine Learning. PMLR, 59017-59065","author":"Tang Sophia","year":"2025","unstructured":"Sophia Tang, Yinuo Zhang, and Pranam Chatterjee. 2025a. PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion. In International Conference on Machine Learning. PMLR, 59017-59065."},{"key":"e_1_3_2_1_31_1","volume-title":"Tr2-d2: Tree search guided trajectory-aware fine-tuning for discrete diffusion. arXiv preprint arXiv:2509.25171","author":"Tang Sophia","year":"2025","unstructured":"Sophia Tang, Yuchen Zhu, Molei Tao, and Pranam Chatterjee. 2025b. Tr2-d2: Tree search guided trajectory-aware fine-tuning for discrete diffusion. arXiv preprint arXiv:2509.25171 (2025)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.5c00789"},{"key":"e_1_3_2_1_33_1","volume-title":"V44, D1","author":"Wang Guangshun","year":"2016","unstructured":"Guangshun Wang, Xia Li, and Zhe Wang. 2016. APD3: the antimicrobial peptide database as a tool for research and education. Nucleic acids research, V44, D1 (2016), D1087-D1093."},{"key":"e_1_3_2_1_34_1","unstructured":"Junqiao Wang Zeng Zhang Yangfan He Zihao Zhang Xinyuan Song Yuyang Song Tianyu Shi Yuchen Li Hengyuan Xu Kunyu Wu Xin Yi Zhongwei Wan Xinhang Yuan Zijun Wang Kuan Lu Menghao Huo Tang Jingqun Guangwu Qian Keqin Li Qiuwu Chen and Lewei He. 2025b. Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey. arXiv:2412.20367 [cs.SE] https:\/\/arxiv.org\/abs\/2412.20367"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0149-6"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00691-9"},{"key":"e_1_3_2_1_37_1","volume-title":"Knowledge-aware Reinforced Language Models for Protein Directed Evolution. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=MikandLqtW","author":"Wang Yuhao","year":"2024","unstructured":"Yuhao Wang, Qiang Zhang, Ming Qin, Xiang Zhuang, Xiaotong Li, Zhichen Gong, Zeyuan Wang, Yu Zhao, Jianhua Yao, Keyan Ding, and Huajun Chen. 2024. Knowledge-aware Reinforced Language Models for Protein Directed Evolution. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=MikandLqtW"},{"key":"e_1_3_2_1_38_1","volume-title":"ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning. arXiv preprint arXiv:2506.07459","author":"Wang Ziwen","year":"2025","unstructured":"Ziwen Wang, Jiajun Fan, Ruihan Guo, Thao Nguyen, Heng Ji, and Ge Liu. 2025a. ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning. arXiv preprint arXiv:2506.07459 (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"2nd AI for Math Workshop@ ICML","author":"Wu Fang","year":"2025","unstructured":"Fang Wu and Yejin Choi. 2025. The invisible leash: Why rlvr may not escape its origin. In 2nd AI for Math Workshop@ ICML 2025."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25662"},{"key":"e_1_3_2_1_41_1","volume-title":"Jure Leskovec, and Yejin Choi.","author":"Wu Fang","year":"2026","unstructured":"Fang Wu, Weihao Xuan, Heli Qi, Hanqun Cao, Heng-Jui Chang, Zeqi Zhou, Haokai Zhao, Ma Jian, Carl Ma, Yu-Chi Cheng, Kuan Pang, Xiangru Tang, Zehong Wang, Guanlue Li, Hanchen Wang, Kejun Ying, Pan Lu, Chiho Im, Seungju Han, Peng Xia, Tinson Xu, Yinxi Li, Deyao Zhu, Pheng-Ann Heng, Naoto Yokoya, Masashi Sugiyama, Li Erran Li, Jure Leskovec, and Yejin Choi. 2026. Proteo-R1: Reasoning Foundation Models for De Novo Protein Design. arXiv:2605.02937 [cs.LG] https:\/\/arxiv.org\/abs\/2605.02937"},{"key":"e_1_3_2_1_42_1","volume-title":"Protein Inverse Folding From Structure Feedback. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ORsrbGTXQB","author":"Xu Junde","year":"2025","unstructured":"Junde Xu, Zijun Gao, Xinyi Zhou, hujie, Xingyi Cheng, Le Song, Guangyong Chen, Pheng-Ann Heng, and Jiezhong Qiu. 2025. Protein Inverse Folding From Structure Feedback. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ORsrbGTXQB"},{"key":"e_1_3_2_1_43_1","volume-title":"International Conference on Machine Learning. PMLR, 38749-38767","author":"Xu Minghao","year":"2023","unstructured":"Minghao Xu, Xinyu Yuan, Santiago Miret, and Jian Tang. 2023b. Protst: Multi-modality learning of protein sequences and biomedical texts. In International Conference on Machine Learning. PMLR, 38749-38767."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.gpb.2023.03.004"},{"key":"e_1_3_2_1_45_1","volume-title":"Improving Protein Sequence Design through Designability Preference Optimization. arXiv preprint arXiv:2506.00297","author":"Xue Fanglei","year":"2025","unstructured":"Fanglei Xue, Andrew Kubaney, Zhichun Guo, Joseph K Min, Ge Liu, Yi Yang, and David Baker. 2025. Improving Protein Sequence Design through Designability Preference Optimization. arXiv preprint arXiv:2506.00297 (2025)."},{"key":"e_1_3_2_1_46_1","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=4OsgYD7em5","author":"Yue Yang","year":"2025","unstructured":"Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, and Gao Huang. 2025. Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=4OsgYD7em5"},{"key":"e_1_3_2_1_47_1","volume-title":"V33, 7","author":"Zhang Yang","year":"2005","unstructured":"Yang Zhang and Jeffrey Skolnick. 2005. TM-align: a protein structure alignment algorithm based on the TM-score. Nucleic acids research, V33, 7 (2005), 2302-2309."},{"key":"e_1_3_2_1_48_1","volume-title":"Echo chamber: Rl post-training amplifies behaviors learned in pretraining. arXiv preprint arXiv:2504.07912","author":"Zhao Rosie","year":"2025","unstructured":"Rosie Zhao, Alexandru Meterez, Sham Kakade, Cengiz Pehlevan, Samy Jelassi, and Eran Malach. 2025. Echo chamber: Rl post-training amplifies behaviors learned in pretraining. arXiv preprint arXiv:2504.07912 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:25:18Z","timestamp":1786065918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":48,"alternative-id":["10.1145\/3770855.3818895","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818895","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}