{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T06:57:32Z","timestamp":1782975452565,"version":"3.54.5"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62202400"],"award-info":[{"award-number":["62202400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/sp63933.2026.00184","type":"proceedings-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:34:20Z","timestamp":1782934460000},"page":"3740-3756","source":"Crossref","is-referenced-by-count":0,"title":["Specializing Language Models for Textual Fuzzing via Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jiayi","family":"Lin","sequence":"first","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangcai","family":"Su","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzhe","family":"Li","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxiong","family":"Qian","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3473932"},{"key":"ref2","volume-title":"OSS-Fuzz.","author":"Arya"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SecDev.2016.043"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23412"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3460319.3464814"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375607"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00071"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639121"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24556"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680389"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00175"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598067"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3622781.3674171"},{"key":"ref15","article-title":"Low-cost and comprehensive non-textual input fuzzing with 11 m -synthesized input generators","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670396"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE55347.2025.00097"},{"key":"ref18","first-page":"6299","article-title":"Hybrid language processor fuzzing via {LLM-Based} constraint solving","volume-title":"34th USENIX Security Symposium (USENIX Security 25)","author":"Yang","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SP63933.2026.00003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref21","article-title":"Compiler-r1: Towards agentic compiler auto-tuning with reinforcement learning","author":"Pan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Swe-rl: Advancing llm reasoning via reinforcement learning on open software evolution","author":"Wei","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Fin-r1: A large language model for financial reasoning through reinforcement learning","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Memory-r1: Enhancing large language model agents to manage and utilize memories via reinforcement learning","author":"Yan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Rlsf: Fine-tuning 1lms via symbolic feedback","author":"Jha","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Logic-rl: Unleashing 11 m reasoning with rule-based reinforcement learning","author":"Xie","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Codei\/o: Condensing reasoning patterns via code input-output prediction","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134020"},{"key":"ref29","volume-title":"Qwen2.5: A party of foundation models","year":"2024"},{"key":"ref30","volume-title":"Introducing OpenAI o3 and o4-mini - openai.com"},{"key":"ref31","volume-title":"AFL++","author":"Heuse","year":"2022"},{"key":"ref32","volume-title":"Fuzzilli in google","year":"2024"},{"key":"ref33","first-page":"209","article-title":"Klee: unassisted and automatic generation of high-coverage tests for complex systems programs","volume":"8","author":"Cadar","year":"2008","journal-title":"OSDI"},{"key":"ref34","first-page":"181","article-title":"Symbolic execution with {SymCC}: Don\u2019t interpret, compile!","volume-title":"29th USENIX Security Symposium (USENIX Security 20)","author":"Poeplau","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2016.23368"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3182657"},{"key":"ref37","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696075"},{"key":"ref39","volume-title":"Source based code coverage","year":"2025"},{"key":"ref40","volume-title":"Openrouter: The unified interface for 11 ms","year":"2026"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2307\/1165329"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/sp54263.2024.00137"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.11613\/BM.2026.010101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598067"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3729398"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-Companion66252.2025.00079"},{"key":"ref47","first-page":"883","article-title":"Fuzzing BusyBox: Leveraging LLM and crash reuse for embedded bug unearthing","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Asmita"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00085"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00211"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690231"},{"key":"ref51","article-title":"Llm-assisted model-based fuzzing of protocol implementations","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Swe-bench: Can language models resolve real-world github issues?","author":"Jimenez","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","author":"Nie","year":"2025","journal-title":"Vulnllm-r: Specialized reasoning llm with agent scaffold for vulnerability detection"},{"key":"ref54","author":"Aditi","year":"2025","journal-title":"Sage: Specificationaware grammar extraction for automated test case generation with llms"},{"key":"ref55","article-title":"Safe rlhf: Safe reinforcement learning from human feedback","author":"Dai","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2026 IEEE Symposium on Security and Privacy (SP)","location":"San Francisco, CA, USA","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["2026 IEEE Symposium on Security and Privacy (SP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11573355\/11573356\/11573566.pdf?arnumber=11573566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:25:57Z","timestamp":1782969957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11573566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/sp63933.2026.00184","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}