{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T02:08:06Z","timestamp":1783908486388,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"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":[[2026,6,13]]},"DOI":"10.1145\/3800645.3812956","type":"proceedings-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T18:41:17Z","timestamp":1781289677000},"page":"1188-1204","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Compass vs Railway Tracks: Unpacking User Mental Models for Communicating Long-Horizon Work to Humans vs. AI"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4944-8477","authenticated-orcid":false,"given":"Savvas","family":"Petridis","sequence":"first","affiliation":[{"name":"Google DeepMind, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8246-8736","authenticated-orcid":false,"given":"Michael Xieyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Google DeepMind, Pittsburgh, Pennsylvania, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8981-1114","authenticated-orcid":false,"given":"Alexander J.","family":"Fiannaca","sequence":"additional","affiliation":[{"name":"Google DeepMind, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9421-7128","authenticated-orcid":false,"given":"Carrie J.","family":"Cai","sequence":"additional","affiliation":[{"name":"Google DeepMind, Mountain View, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1941-939X","authenticated-orcid":false,"given":"Michael","family":"Terry","sequence":"additional","affiliation":[{"name":"Google DeepMind, Cambridge, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Anthropic. 2025. Introducing Claude Sonnet 4.5. https:\/\/www.anthropic.com\/news\/claude-sonnet-4-5"},{"key":"e_1_3_3_2_3_2","unstructured":"Anthropic. 2025. Rakuten accelerates development with Claude Code. https:\/\/www.anthropic.com\/customers\/rakuten"},{"key":"e_1_3_3_2_4_2","unstructured":"Anthropic. 2026. Claude Code overview. https:\/\/code.claude.com\/docs\/en\/overview"},{"key":"e_1_3_3_2_5_2","unstructured":"Anthropic. 2026. Introducing Cowork | Claude. https:\/\/claude.com\/blog\/cowork-research-preview"},{"key":"e_1_3_3_2_6_2","unstructured":"Michael\u00a0S. Bernstein Joel Brandt Robert\u00a0C. Miller and David\u00a0R. Karger. 2011. Crowds in two seconds: Enabling realtime crowd-powered interfaces. MIT web domain (Oct. 2011). https:\/\/dspace.mit.edu\/handle\/1721.1\/72377 Accepted: 2012-08-28T18:02:44Z ISBN: 9781450307161."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0S. Bernstein Greg Little Robert\u00a0C. Miller Bj\u00f6rn Hartmann Mark\u00a0S. Ackerman David\u00a0R. Karger David Crowell and Katrina Panovich. 2015. Soylent: a word processor with a crowd inside. Commun. ACM 58 8 (July 2015) 85\u201394. 10.1145\/2791285","DOI":"10.1145\/2791285"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Stephen Brade Bryan Wang Mauricio Sousa Sageev Oore and Tovi Grossman. 2023. Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models. 10.48550\/arXiv.2304.09337arXiv:https:\/\/arXiv.org\/abs\/2304.09337 [cs].","DOI":"10.48550\/arXiv.2304.09337"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology 3 2 (2006) 77\u2013101.","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_2_10_2","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems , Vol.\u00a033. 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_3_2_11_2","unstructured":"Raluca Budiu Feifei Liu Amy Zhang and Emma Cionca. 2023. Prompt Structure in Conversations with Generative AI. https:\/\/www.nngroup.com\/articles\/ai-prompt-structure\/"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Haichao Chen Zehua Jiang Xinyu Liu Can\u00a0Can Xue Samantha Min\u00a0Er Yew Bin Sheng Ying-Feng Zheng Xiaofei Wang You Wu Sobha Sivaprasad Tien\u00a0Yin Wong Varun Chaudhary and Yih\u00a0Chung Tham. 2025. Can large language models fully automate or partially assist paper selection in systematic reviews? The British Journal of Ophthalmology 109 8 (Jan. 2025) e326254. 10.1136\/bjo-2024-326254","DOI":"10.1136\/bjo-2024-326254"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung\u00a0Won Chung Charles Sutton Sebastian Gehrmann Parker Schuh Kensen Shi Sasha Tsvyashchenko Joshua Maynez Abhishek Rao Parker Barnes Yi Tay Noam Shazeer Vinodkumar Prabhakaran Emily Reif Nan Du Ben Hutchinson Reiner Pope James Bradbury Jacob Austin Michael Isard Guy Gur-Ari Pengcheng Yin Toju Duke Anselm Levskaya Sanjay Ghemawat Sunipa Dev Henryk Michalewski Xavier Garcia Vedant Misra Kevin Robinson Liam Fedus Denny Zhou Daphne Ippolito David Luan Hyeontaek Lim Barret Zoph Alexander Spiridonov Ryan Sepassi David Dohan Shivani Agrawal Mark Omernick Andrew\u00a0M. Dai Thanumalayan\u00a0Sankaranarayana Pillai Marie Pellat Aitor Lewkowycz Erica Moreira Rewon Child Oleksandr Polozov Katherine Lee Zongwei Zhou Xuezhi Wang Brennan Saeta Mark Diaz Orhan Firat Michele Catasta Jason Wei Kathy Meier-Hellstern Douglas Eck Jeff Dean Slav Petrov and Noah Fiedel. 2022. PaLM: Scaling Language Modeling with Pathways. 10.48550\/arXiv.2204.02311arXiv:https:\/\/arXiv.org\/abs\/2204.02311 [cs].","DOI":"10.48550\/arXiv.2204.02311"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Hyung\u00a0Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang\u00a0Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Alex Castro-Ros Marie Pellat Kevin Robinson Dasha Valter Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed\u00a0H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc\u00a0V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. 10.48550\/arXiv.2210.11416arXiv:https:\/\/arXiv.org\/abs\/2210.11416 [cs].","DOI":"10.48550\/arXiv.2210.11416"},{"key":"e_1_3_3_2_15_2","unstructured":"Cursor. 2026. Cursor. https:\/\/cursor.com"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580969"},{"key":"e_1_3_3_2_17_2","unstructured":"Google DeepMind. 2025. Gemini Deep Research \u2014 your personal research assistant. https:\/\/gemini.google\/overview\/deep-research\/"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Anhai Doan Raghu Ramakrishnan and Alon\u00a0Y. Halevy. 2011. Crowdsourcing systems on the World-Wide Web. Commun. ACM 54 4 (April 2011) 86\u201396. 10.1145\/1924421.1924442","DOI":"10.1145\/1924421.1924442"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1979742.1979826"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"K.\u00a0J.\u00a0Kevin Feng Kevin Pu Matt Latzke Tal August Pao Siangliulue Jonathan Bragg Daniel\u00a0S. Weld Amy\u00a0X. Zhang and Joseph\u00a0Chee Chang. 2025. Cocoa: Co-Planning and Co-Execution with AI Agents. 10.48550\/arXiv.2412.10999arXiv:https:\/\/arXiv.org\/abs\/2412.10999 [cs].","DOI":"10.48550\/arXiv.2412.10999"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Adam Fourney Gagan Bansal Hussein Mozannar Cheng Tan Eduardo Salinas Erkang Zhu Friederike Niedtner Grace Proebsting Griffin Bassman Jack Gerrits Jacob Alber Peter Chang Ricky Loynd Robert West Victor Dibia Ahmed Awadallah Ece Kamar Rafah Hosn and Saleema Amershi. 2024. Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks. 10.48550\/arXiv.2411.04468arXiv:https:\/\/arXiv.org\/abs\/2411.04468 [cs].","DOI":"10.48550\/arXiv.2411.04468"},{"key":"e_1_3_3_2_22_2","unstructured":"Google. 2025. A2UI. https:\/\/a2ui.org\/"},{"key":"e_1_3_3_2_23_2","unstructured":"Google. 2025. Agent Development Kit. https:\/\/google.github.io\/adk-docs"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Xinyi Hou Yanjie Zhao Yue Liu Zhou Yang Kailong Wang Li Li Xiapu Luo David Lo John Grundy and Haoyu Wang. 2024. Large Language Models for Software Engineering: A Systematic Literature Review. 10.48550\/arXiv.2308.10620arXiv:https:\/\/arXiv.org\/abs\/2308.10620 [cs].","DOI":"10.48550\/arXiv.2308.10620"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Jiajie Huang Honghao Lai Weilong Zhao Danni Xia Chunyang Bai Mingyao Sun Jianing Liu Jiayi Liu Bei Pan Jinhui Tian and Long Ge. 2025. Large Language Model\u2013Assisted Risk-of-Bias Assessment in Randomized Controlled Trials Using the Revised Risk-of-Bias Tool: Evaluation Study. Journal of Medical Internet Research 27 1 (June 2025) e70450. 10.2196\/70450Company: Journal of Medical Internet Research Distributor: Journal of Medical Internet Research Institution: Journal of Medical Internet Research Label: Journal of Medical Internet Research.","DOI":"10.2196\/70450"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Minsuk Kahng Ian Tenney Mahima Pushkarna Michael\u00a0Xieyang Liu James Wexler Emily Reif Krystal Kallarackal Minsuk Chang Michael Terry and Lucas Dixon. 2024. LLM Comparator: Interactive Analysis of Side-by-Side Evaluation of Large Language Models. IEEE Transactions on Visualization and Computer Graphics (2024) 1\u201311. 10.1109\/TVCG.2024.3456354Conference Name: IEEE Transactions on Visualization and Computer Graphics.","DOI":"10.1109\/TVCG.2024.3456354"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650755"},{"key":"e_1_3_3_2_28_2","unstructured":"Kiro. 2025. Specs - Docs - Kiro: The AI IDE for prototype to production. https:\/\/kiro.dev\/docs\/specs\/"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2441776.2441923"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2047196.2047202"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/1979742.1979865"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel Sebastian Riedel and Douwe Kiela. 2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. 10.48550\/arXiv.2005.11401arXiv:https:\/\/arXiv.org\/abs\/2005.11401 [cs].","DOI":"10.48550\/arXiv.2005.11401"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","unstructured":"Franklin\u00a0Mingzhe Li Michael\u00a0Xieyang Liu Cynthia\u00a0L. Bennett and Shaun\u00a0K. Kane. 2026. ADCanvas: Accessible and Conversational Audio Description Authoring for Blind and Low Vision Creators. 10.1145\/3772318.3791158arXiv:https:\/\/arXiv.org\/abs\/2602.07266 [cs].","DOI":"10.1145\/3772318.3791158"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","unstructured":"Jenny\u00a0T. Liang Melissa Lin Nikitha Rao and Brad\u00a0A. Myers. 2025. Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts. Proc. ACM Softw. Eng. 2 FSE (June 2025) FSE072:1591\u2013FSE072:1614. 10.1145\/3729342","DOI":"10.1145\/3729342"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/1837885.1837907"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866040"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0Xieyang Liu Aniket Kittur and Brad\u00a0A. Myers. 2021. To Reuse or Not To Reuse? A Framework and System for Evaluating Summarized Knowledge. Proceedings of the ACM on Human-Computer Interaction 5 CSCW1 (April 2021) 166:1\u2013166:35. 10.1145\/3449240","DOI":"10.1145\/3449240"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501968"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0Xieyang Liu Frederick Liu Alexander\u00a0J. Fiannaca Terry Koo Lucas Dixon Michael Terry and Carrie\u00a0J. Cai. 2024. \"We Need Structured Output\": Towards User-centered Constraints on Large Language Model Output. 10.1145\/3613905.3650756arXiv:https:\/\/arXiv.org\/abs\/2404.07362 [cs].","DOI":"10.1145\/3613905.3650756"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0Xieyang Liu Savvas Petridis Vivian Tsai Alexander\u00a0J. Fiannaca Alex Olwal Michael Terry and Carrie\u00a0J. Cai. 2025. Gensors: Authoring Personalized Visual Sensors with Multimodal Foundation Models and Reasoning. 10.1145\/3708359.3712085arXiv:https:\/\/arXiv.org\/abs\/2501.15727 [cs].","DOI":"10.1145\/3708359.3712085"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580817"},{"key":"e_1_3_3_2_42_2","unstructured":"Michael\u00a0Xieyang Liu Michael Terry Alex Olwal Savvas Petridis Vivian Tsai Alexander Fiannaca and Carrie\u00a0J. Cai. 2025. Meta-Sensors: Self-Discovery Adaptation and Reasoning. Defensive Publications Series (March 2025). https:\/\/www.tdcommons.org\/dpubs_series\/7863"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642149"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858288"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","unstructured":"Qianou Ma Weirui Peng Hua Shen Kenneth Koedinger and Tongshuang Wu. 2024. What You Say = What You Want? Teaching Humans to Articulate Requirements for LLMs. 10.48550\/arXiv.2409.08775arXiv:https:\/\/arXiv.org\/abs\/2409.08775 [cs].","DOI":"10.48550\/arXiv.2409.08775"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Aman Madaan Niket Tandon Prakhar Gupta Skyler Hallinan Luyu Gao Sarah Wiegreffe Uri Alon Nouha Dziri Shrimai Prabhumoye Yiming Yang Shashank Gupta Bodhisattwa\u00a0Prasad Majumder Katherine Hermann Sean Welleck Amir Yazdanbakhsh and Peter Clark. 2023. Self-Refine: Iterative Refinement with Self-Feedback. 10.48550\/arXiv.2303.17651arXiv:https:\/\/arXiv.org\/abs\/2303.17651 [cs].","DOI":"10.48550\/arXiv.2303.17651"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642861"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650947"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858539"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Ali Modarressi Abdullatif K\u00f6ksal Ayyoob Imani Mohsen Fayyaz and Hinrich Sch\u00fctze. 2025. MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory. 10.48550\/arXiv.2404.11672arXiv:https:\/\/arXiv.org\/abs\/2404.11672 [cs].","DOI":"10.48550\/arXiv.2404.11672"},{"key":"e_1_3_3_2_51_2","unstructured":"Kate Moran. 2024. CARE: Structure for Crafting AI Prompts. https:\/\/www.nngroup.com\/articles\/careful-prompts\/"},{"key":"e_1_3_3_2_52_2","unstructured":"Tim Neusesser and Kate Moran. 2025. Designing Use-Case Prompt Suggestions. https:\/\/www.nngroup.com\/articles\/designing-use-case-prompt-suggestions\/"},{"key":"e_1_3_3_2_53_2","unstructured":"Alex Olwal Michael\u00a0Xieyang Liu Savvas Petridis Vivian Tsai Alexander Fiannaca Michael Terry and Carrie Cai. 2025. Semantic Sensors: Multimodal Language Model Powered Sensors Capable of Reasoning. Defensive Publications Series (June 2025). https:\/\/www.tdcommons.org\/dpubs_series\/8210"},{"key":"e_1_3_3_2_54_2","unstructured":"OpenAI. 2024. Introducing SWE-bench Verified. https:\/\/openai.com\/index\/introducing-swe-bench-verified\/"},{"key":"e_1_3_3_2_55_2","unstructured":"OpenAI. 2025. Introducing deep research. https:\/\/openai.com\/index\/introducing-deep-research\/"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul\u00a0F. Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (Dec. 2022) 27730\u201327744. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/b1efde53be364a73914f58805a001731-Abstract-Conference.html","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","unstructured":"Chris Parnin Gustavo Soares Rahul Pandita Sumit Gulwani Jessica Rich and Austin\u00a0Z. Henley. 2023. Building Your Own Product Copilot: Challenges Opportunities and Needs. 10.48550\/arXiv.2312.14231arXiv:https:\/\/arXiv.org\/abs\/2312.14231 [cs].","DOI":"10.48550\/arXiv.2312.14231"},{"key":"e_1_3_3_2_58_2","unstructured":"Perplexity. 2025. Introducing Perplexity Deep Research. https:\/\/www.perplexity.ai\/hub\/blog\/introducing-perplexity-deep-research"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/VL\/HCC60511.2024.00023"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3585628"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","unstructured":"Savvas Petridis Michael Terry and Carrie\u00a0J. Cai. 2023. PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers\u2019 Workflows. 10.48550\/arXiv.2310.15435arXiv:https:\/\/arXiv.org\/abs\/2310.15435 [cs].","DOI":"10.48550\/arXiv.2310.15435"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645144"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","unstructured":"Crystal Qian Michael\u00a0Xieyang Liu Emily Reif Grady Simon Nada Hussein Nathan Clement James Wexler Carrie\u00a0J. Cai Michael Terry and Minsuk Kahng. 2024. The Evolution of LLM Adoption in Industry Data Curation Practices. 10.48550\/arXiv.2412.16089arXiv:https:\/\/arXiv.org\/abs\/2412.16089 [cs].","DOI":"10.48550\/arXiv.2412.16089"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719677"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3716291"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642400"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian\u00a0Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit\u00a0Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric\u00a0Michael Smith Ranjan Subramanian Xiaoqing\u00a0Ellen Tan Binh Tang Ross Taylor Adina Williams Jian\u00a0Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. 10.48550\/arXiv.2307.09288arXiv:https:\/\/arXiv.org\/abs\/2307.09288 [cs].","DOI":"10.48550\/arXiv.2307.09288"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","unstructured":"Mojtaba Vaismoradi Hannele Turunen and Terese Bondas. 2013. Content analysis and thematic analysis: Implications for conducting a qualitative descriptive study. Nursing & Health Sciences 15 3 (2013) 398\u2013405. 10.1111\/nhs.12048_eprint: https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/nhs.12048.","DOI":"10.1111\/nhs.12048"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Eric von Hippel. 1986. Lead Users: A Source of Novel Product Concepts. Manage. Sci. 32 7 (July 1986) 791\u2013805.","DOI":"10.1287\/mnsc.32.7.791"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. 2023. Voyager: An Open-Ended Embodied Agent with Large Language Models. 10.48550\/arXiv.2305.16291arXiv:https:\/\/arXiv.org\/abs\/2305.16291 [cs].","DOI":"10.48550\/arXiv.2305.16291"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","unstructured":"Xingyao Wang Boxuan Li Yufan Song Frank\u00a0F. Xu Xiangru Tang Mingchen Zhuge Jiayi Pan Yueqi Song Bowen Li Jaskirat Singh Hoang\u00a0H. Tran Fuqiang Li Ren Ma Mingzhang Zheng Bill Qian Yanjun Shao Niklas Muennighoff Yizhe Zhang Binyuan Hui Junyang Lin Robert Brennan Hao Peng Heng Ji and Graham Neubig. 2025. OpenHands: An Open Platform for AI Software Developers as Generalist Agents. 10.48550\/arXiv.2407.16741arXiv:https:\/\/arXiv.org\/abs\/2407.16741 [cs].","DOI":"10.48550\/arXiv.2407.16741"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","unstructured":"Xuezhi Wang Jason Wei Dale Schuurmans Quoc Le Ed Chi Sharan Narang Aakanksha Chowdhery and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. 10.48550\/arXiv.2203.11171arXiv:https:\/\/arXiv.org\/abs\/2203.11171 [cs].","DOI":"10.48550\/arXiv.2203.11171"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642803"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","unstructured":"Jason Wei Maarten Bosma Vincent\u00a0Y. Zhao Kelvin Guu Adams\u00a0Wei Yu Brian Lester Nan Du Andrew\u00a0M. Dai and Quoc\u00a0V. Le. 2022. Finetuned Language Models Are Zero-Shot Learners. 10.48550\/arXiv.2109.01652arXiv:https:\/\/arXiv.org\/abs\/2109.01652 [cs].","DOI":"10.48550\/arXiv.2109.01652"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed Chi Quoc Le and Denny Zhou. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. 10.48550\/arXiv.2201.11903arXiv:https:\/\/arXiv.org\/abs\/2201.11903 [cs].","DOI":"10.48550\/arXiv.2201.11903"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","unstructured":"Jules White Quchen Fu Sam Hays Michael Sandborn Carlos Olea Henry Gilbert Ashraf Elnashar Jesse Spencer-Smith and Douglas\u00a0C. Schmidt. 2023. A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT. 10.48550\/arXiv.2302.11382arXiv:https:\/\/arXiv.org\/abs\/2302.11382 [cs].","DOI":"10.48550\/arXiv.2302.11382"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","unstructured":"Jason Wu Eldon Schoop Alan Leung Titus Barik Jeffrey\u00a0P. Bigham and Jeffrey Nichols. 2024. UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback. 10.48550\/arXiv.2406.07739arXiv:https:\/\/arXiv.org\/abs\/2406.07739 [cs].","DOI":"10.48550\/arXiv.2406.07739"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","unstructured":"Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Beibin Li Erkang Zhu Li Jiang Xiaoyun Zhang Shaokun Zhang Jiale Liu Ahmed\u00a0Hassan Awadallah Ryen\u00a0W. White Doug Burger and Chi Wang. 2023. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation. 10.48550\/arXiv.2308.08155arXiv:https:\/\/arXiv.org\/abs\/2308.08155 [cs].","DOI":"10.48550\/arXiv.2308.08155"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519729"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517582"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","unstructured":"Chunqiu\u00a0Steven Xia Yinlin Deng Soren Dunn and Lingming Zhang. 2024. Agentless: Demystifying LLM-based Software Engineering Agents. 10.48550\/arXiv.2407.01489arXiv:https:\/\/arXiv.org\/abs\/2407.01489 [cs].","DOI":"10.48550\/arXiv.2407.01489"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","unstructured":"Fengli Xu Qianyue Hao Zefang Zong Jingwei Wang Yunke Zhang Jingyi Wang Xiaochong Lan Jiahui Gong Tianjian Ouyang Fanjin Meng Chenyang Shao Yuwei Yan Qinglong Yang Yiwen Song Sijian Ren Xinyuan Hu Yu Li Jie Feng Chen Gao and Yong Li. 2025. Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models. 10.48550\/arXiv.2501.09686arXiv:https:\/\/arXiv.org\/abs\/2501.09686 [cs] version: 3.","DOI":"10.48550\/arXiv.2501.09686"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"publisher","unstructured":"Chenyang Yang Yike Shi Qianou Ma Michael\u00a0Xieyang Liu Christian K\u00e4stner and Tongshuang Wu. 2025. What Prompts Don\u2019t Say: Understanding and Managing Underspecification in LLM Prompts. 10.48550\/arXiv.2505.13360arXiv:https:\/\/arXiv.org\/abs\/2505.13360 [cs].","DOI":"10.48550\/arXiv.2505.13360"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","unstructured":"John Yang Carlos\u00a0E. Jimenez Alexander Wettig Kilian Lieret Shunyu Yao Karthik Narasimhan and Ofir Press. 2024. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. 10.48550\/arXiv.2405.15793arXiv:https:\/\/arXiv.org\/abs\/2405.15793.","DOI":"10.48550\/arXiv.2405.15793"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","unstructured":"John Yang Carlos\u00a0E. Jimenez Alex\u00a0L. Zhang Kilian Lieret Joyce Yang Xindi Wu Ori Press Niklas Muennighoff Gabriel Synnaeve Karthik\u00a0R. Narasimhan Diyi Yang Sida\u00a0I. Wang and Ofir Press. 2024. SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?10.48550\/arXiv.2410.03859arXiv:https:\/\/arXiv.org\/abs\/2410.03859 [cs].","DOI":"10.48550\/arXiv.2410.03859"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Thomas\u00a0L. Griffiths Yuan Cao and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. 10.48550\/arXiv.2305.10601arXiv:https:\/\/arXiv.org\/abs\/2305.10601 [cs].","DOI":"10.48550\/arXiv.2305.10601"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik Narasimhan and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. 10.48550\/arXiv.2210.03629arXiv:https:\/\/arXiv.org\/abs\/2210.03629.","DOI":"10.48550\/arXiv.2210.03629"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","unstructured":"Quanjun Zhang Chunrong Fang Yang Xie Yaxin Zhang Yun Yang Weisong Sun Shengcheng Yu and Zhenyu Chen. 2024. A Survey on Large Language Models for Software Engineering. 10.48550\/arXiv.2312.15223arXiv:https:\/\/arXiv.org\/abs\/2312.15223 [cs].","DOI":"10.48550\/arXiv.2312.15223"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"publisher","unstructured":"Shengyu Zhang Linfeng Dong Xiaoya Li Sen Zhang Xiaofei Sun Shuhe Wang Jiwei Li Runyi Hu Tianwei Zhang Fei Wu and Guoyin Wang. 2025. Instruction Tuning for Large Language Models: A Survey. 10.48550\/arXiv.2308.10792arXiv:https:\/\/arXiv.org\/abs\/2308.10792 [cs] version: 9.","DOI":"10.48550\/arXiv.2308.10792"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713905"}],"event":{"name":"DIS '26: Designing Interactive Systems Conference","location":"Singapore , Singapore","acronym":"DIS '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 Designing Interactive Systems Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3800645.3812956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T01:36:44Z","timestamp":1783906604000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3800645.3812956"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":90,"alternative-id":["10.1145\/3800645.3812956","10.1145\/3800645"],"URL":"https:\/\/doi.org\/10.1145\/3800645.3812956","relation":{},"subject":[],"published":{"date-parts":[[2026,6,12]]},"assertion":[{"value":"2026-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}