{"url":"/task/user-simulation","name":"User Simulation","slug":"user-simulation","description_markdown":"Simulation of user interacting with a dialog system","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":64,"papers_with_code":25,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/lmsys-usp","name":"LMSYS-USP","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vmd","name":"VMD","full_name":"Virtual Moderation Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/goal-oriented-dialog","name":"Goal-Oriented Dialog"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":25,"of":25,"tagged_in_all":64,"items":[{"url":"/paper/a-user-simulator-for-task-completion","title":"A User Simulator for Task-Completion Dialogues","date":"2016-12-17","arxiv_id":"1612.05688","repositories_listed":10,"syntology":null},{"url":"/paper/kuairec-a-fully-observed-dataset-for","title":"KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems","date":"2022-02-22","arxiv_id":"2202.10842","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/in-context-learning-user-simulators-for-task","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","date":"2023-06-01","arxiv_id":"2306.00774","repositories_listed":2,"syntology":null},{"url":"/paper/crosswoz-a-large-scale-chinese-cross-domain","title":"CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset","date":"2020-02-27","arxiv_id":"2002.11893","repositories_listed":2,"syntology":null},{"url":"/paper/thought-augmented-planning-for-llm-powered","title":"Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent","date":"2025-06-30","arxiv_id":"2506.23485","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-human-like-thinking-in-search","title":"Exploring Human-Like Thinking in Search Simulations with Large Language Models","date":"2025-04-10","arxiv_id":"2504.07570","repositories_listed":1,"syntology":null},{"url":"/paper/flow-a-feedback-loop-framework-for","title":"Agentic Feedback Loop Modeling Improves Recommendation and User Simulation","date":"2024-10-26","arxiv_id":"2410.20027","repositories_listed":1,"syntology":null},{"url":"/paper/multi-trait-user-simulation-with-adaptive","title":"Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants","date":"2024-10-16","arxiv_id":"2410.12891","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/towards-a-formal-characterization-of-user","title":"Towards a Formal Characterization of User Simulation Objectives in Conversational Information Access","date":"2024-06-27","arxiv_id":"2406.19007","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/identifying-breakdowns-in-conversational","title":"Identifying Breakdowns in Conversational Recommender Systems using User Simulation","date":"2024-05-23","arxiv_id":"2405.14249","repositories_listed":1,"syntology":null},{"url":"/paper/lusifer-llm-based-user-simulated-feedback","title":"Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems","date":"2024-05-22","arxiv_id":"2405.13362","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-robustness-of","title":"Investigating the Robustness of Counterfactual Learning to Rank Models: A Reproducibility Study","date":"2024-04-04","arxiv_id":"2404.03707","repositories_listed":1,"syntology":null},{"url":"/paper/usimagent-large-language-models-for","title":"USimAgent: Large Language Models for Simulating Search Users","date":"2024-03-14","arxiv_id":"2403.09142","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/unveiling-the-truth-and-facilitating-change","title":"Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation","date":"2024-02-26","arxiv_id":"2402.16333","repositories_listed":1,"syntology":null},{"url":"/paper/recagent-a-novel-simulation-paradigm-for","title":"User Behavior Simulation with Large Language Model based Agents","date":"2023-06-05","arxiv_id":"2306.02552","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-interactive-lung-lesion","title":"Multimodal Interactive Lung Lesion Segmentation: A Framework for Annotating PET/CT Images based on Physiological and Anatomical Cues","date":"2023-01-24","arxiv_id":"2301.09914","repositories_listed":1,"syntology":null},{"url":"/paper/usersimcrs-a-user-simulation-toolkit-for","title":"UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems","date":"2023-01-13","arxiv_id":"2301.05544","repositories_listed":1,"syntology":null},{"url":"/paper/botsim-an-end-to-end-bot-simulation-toolkit","title":"BotSIM: An End-to-End Bot Simulation Toolkit for Commercial Task-Oriented Dialog Systems","date":"2022-11-29","arxiv_id":"2211.15916","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-and-simulating-user-utterance","title":"Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems","date":"2022-05-03","arxiv_id":"2205.01763","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-mixed-initiative-conversational","title":"Evaluating Mixed-initiative Conversational Search Systems via User Simulation","date":"2022-04-17","arxiv_id":"2204.08046","repositories_listed":1,"syntology":null},{"url":"/paper/reactive-and-safe-road-user-simulations-using","title":"Reactive and Safe Road User Simulations using Neural Barrier Certificates","date":"2021-09-14","arxiv_id":"2109.06689","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-user-satisfaction-for-the","title":"Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems","date":"2021-05-08","arxiv_id":"2105.03748","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-conversational-recommender-systems","title":"Evaluating Conversational Recommender Systems via User Simulation","date":"2020-06-15","arxiv_id":"2006.08732","repositories_listed":1,"syntology":null},{"url":"/paper/variational-hierarchical-dialog-autoencoder","title":"Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation","date":"2020-01-23","arxiv_id":"2001.08604","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-build-user-simulators-to-train-rl","title":"How to Build User Simulators to Train RL-based Dialog Systems","date":"2019-09-03","arxiv_id":"1909.01388","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}