{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:05:47Z","timestamp":1784300747644,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,5]]},"DOI":"10.1145\/3803437.3805208","type":"proceedings-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:27:39Z","timestamp":1784298459000},"page":"345-350","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["How Far Can VLMs Go for Visual Bug Detection? Studying 19,738 Keyframes from 41 Hours of Gameplay Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8640-7622","authenticated-orcid":false,"given":"Wentao","family":"Lu","sequence":"first","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8129-4204","authenticated-orcid":false,"given":"Alexander","family":"Senchenko","sequence":"additional","affiliation":[{"name":"Electronic Arts, Vancouver, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2774-1024","authenticated-orcid":false,"given":"Alan","family":"Sayle","sequence":"additional","affiliation":[{"name":"Electronic Arts, Guildford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4373-4958","authenticated-orcid":false,"given":"Abram","family":"Hindle","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0474-5718","authenticated-orcid":false,"given":"Cor-Paul","family":"Bezemer","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2025. FFmpeg. https:\/\/ffmpeg.org\/"},{"key":"e_1_3_2_1_2_1","volume-title":"Software Test Design: Write Comprehensive Test Plans to Uncover Critical Bugs in Web, Desktop, and Mobile Apps","author":"Amey Simon","unstructured":"Simon Amey. 2022. Software Test Design: Write Comprehensive Test Plans to Uncover Critical Bugs in Web, Desktop, and Mobile Apps. Packt Publishing, Birmingham, UK."},{"key":"e_1_3_2_1_3_1","unstructured":"Atlassian. 2025. Jira. https:\/\/www.atlassian.com\/software\/jira"},{"key":"e_1_3_2_1_4_1","unstructured":"Mirco Bonomo and Simone Bianco. 2025. Visual RAG: Expanding MLLM visual knowledge without fine-tuning. arXiv:2501.10834 [cs.CV] https:\/\/arxiv.org\/abs\/2501.10834"},{"key":"e_1_3_2_1_5_1","volume-title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=dbFEFHAD79","author":"Chen Dongping","year":"2024","unstructured":"Dongping Chen, Ruoxi Chen, Shilin Zhang, Yaochen Wang, Yinuo Liu, Huichi Zhou, Qihui Zhang, Yao Wan, Pan Zhou, and Lichao Sun. 2024. MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=dbFEFHAD79"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731120.3744588"},{"key":"e_1_3_2_1_7_1","unstructured":"Zongcan Ding Haodong Zhang Peng Wu Guansong Pang Zhiwei Yang Peng Wang and Yanning Zhang. 2025. SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model. arXiv:2504.10320 [cs.CV] https:\/\/arxiv.org\/abs\/2504.10320"},{"key":"e_1_3_2_1_8_1","unstructured":"elastic. 2025. OPEN SOURCE SEARCH ANALYTICS AND AI PLATFORM. https:\/\/www.elastic.co\/elasticsearch"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695992"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Emanuela Guglielmi Simone Scalabrino Gabriele Bavota and Rocco Oliveto. 2022. Towards Using Gameplay Videos for Detecting Issues in Video Games. arXiv:2204.04182 [cs.SE] https:\/\/arxiv.org\/abs\/2204.04182","DOI":"10.1007\/s10664-023-10365-0"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-023-10365-0"},{"key":"e_1_3_2_1_12_1","unstructured":"Haitao Li Qian Dong Junjie Chen Huixue Su Yujia Zhou Qingyao Ai Ziyi Ye and Yiqun Liu. 2024. LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods. arXiv:2412.05579 [cs.CL] https:\/\/arxiv.org\/abs\/2412.05579"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-019-09733-6"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3505464.3505474"},{"key":"e_1_3_2_1_15_1","unstructured":"Jingyu Liu Jiaen Lin and Yong Liu. 2024. How Much Can RAG Help the Reasoning of LLM? arXiv:2410.02338 [cs.CL] https:\/\/arxiv.org\/abs\/2410.02338"},{"key":"e_1_3_2_1_16_1","unstructured":"Wentao Lu Alexander Senchenko Abram Hindle and Cor-Paul Bezemer. 2025. Automated Bug Frame Retrieval from Gameplay Videos Using Vision-Language Models. arXiv:2508.04895 [cs.SE] https:\/\/arxiv.org\/abs\/2508.04895"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Finlay Macklon and Cor-Paul Bezemer. 2025. Exploring the Capabilities of Vision-Language Models to Detect Visual Bugs in HTML5 <canvas> Applications. arXiv:2501.09236 [cs.SE] https:\/\/arxiv.org\/abs\/2501.09236","DOI":"10.1007\/s10664-026-10906-3"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc8090115"},{"key":"e_1_3_2_1_19_1","unstructured":"Microsoft. 2025. Azure. https:\/\/azure.microsoft.com\/en-ca"},{"key":"e_1_3_2_1_20_1","unstructured":"Ollama. 2024. gte-Qwen2-1.5B-instruct. https:\/\/ollama.com\/rjmalagon\/gte-qwen2-1.5b-instruct-embed-f16"},{"key":"e_1_3_2_1_21_1","unstructured":"OpenAI. 2021. clip-vit-base-patch32. https:\/\/huggingface.co\/openai\/clip-vit-base-patch32"},{"key":"e_1_3_2_1_22_1","unstructured":"OPENAI. 2024. GPT-4.1 mini. https:\/\/platform.openai.com\/docs\/models\/gpt-4.1-mini"},{"key":"e_1_3_2_1_23_1","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o"},{"key":"e_1_3_2_1_24_1","unstructured":"OpenAI. 2025. OpenAI. https:\/\/openai.com\/"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00144"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02118"},{"key":"e_1_3_2_1_27_1","unstructured":"Mohammad Reza Taesiri Abhijay Ghildyal Saman Zadtootaghaj Nabajeet Barman and Cor-Paul Bezemer. 2025. VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance. arXiv:2505.15952 [cs.CV] https:\/\/arxiv.org\/abs\/2505.15952"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528438"},{"key":"e_1_3_2_1_29_1","volume-title":"Eduardo Santana de Almeida, and Iftekhar Ahmed","author":"Truelove Andrew","year":"2023","unstructured":"Andrew Truelove, Shiyue Rong, Eduardo Santana de Almeida, and Iftekhar Ahmed. 2023. Finding the Needle in a Haystack: Detecting Bug Occurrences in Gameplay Videos. arXiv:2311.10926 [cs.SE] https:\/\/arxiv.org\/abs\/2311.10926"},{"key":"e_1_3_2_1_30_1","unstructured":"Pat Verga Sebastian Hofstatter Sophia Althammer Yixuan Su Aleksandra Piktus Arkady Arkhangorodsky Minjie Xu Naomi White and Patrick Lewis. 2024. Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models. arXiv:2404.18796 [cs.CL] https:\/\/arxiv.org\/abs\/2404.18796"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v21i1.36820"}],"event":{"name":"FSE Companion '26: 34th ACM International Conference on the Foundations of Software Engineering","location":"Concordia University Montreal QC Canada","acronym":"FSE Companion '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 34th ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3803437.3805208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:27:55Z","timestamp":1784298475000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3803437.3805208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":31,"alternative-id":["10.1145\/3803437.3805208","10.1145\/3803437"],"URL":"https:\/\/doi.org\/10.1145\/3803437.3805208","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}