{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/interactive-recommendation","name":"Interactive Recommendation","slug":"interactive-recommendation","description_markdown":null,"categories":[{"name":"Graphs","url":"/area/graphs"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":40,"papers_with_code":10,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/recommendation-systems","name":"Recommendation Systems"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":40,"of":40,"of_with_code":10,"tagged_in_all":40,"counts":{"archive_papers_tagged":40,"with_a_code_link":10,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":40,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/alleviating-matthew-effect-of-offline","slug":"alleviating-matthew-effect-of-offline","title":"Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation","date":"2023-07-10","arxiv_id":"2307.04571","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/alleviating-matthew-effect-of-offline#ran","syntology_url":"https://syntology.ai/paper/2307.04571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04571"}},"official":{"repos":["chongminggao/dorl-codes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/thought-augmented-planning-for-llm-powered","slug":"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/contrastive-representation-for-interactive","slug":"contrastive-representation-for-interactive","title":"Contrastive Representation for Interactive Recommendation","date":"2024-12-24","arxiv_id":"2412.18396","repositories_listed":1,"syntology":null},{"url":"/paper/kuairand-an-unbiased-sequential","slug":"kuairand-an-unbiased-sequential","title":"KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos","date":"2022-08-18","arxiv_id":"2208.08696","repositories_listed":1,"syntology":null},{"url":"/paper/modelling-users-with-item-metadata-for","slug":"modelling-users-with-item-metadata-for","title":"Modelling Users with Item Metadata for Explainable and Interactive Recommendation","date":"2022-07-01","arxiv_id":"2207.00350","repositories_listed":1,"syntology":null},{"url":"/paper/cirs-bursting-filter-bubbles-by","slug":"cirs-bursting-filter-bubbles-by","title":"CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System","date":"2022-04-04","arxiv_id":"2204.01266","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cirs-bursting-filter-bubbles-by#ran","syntology_url":"https://syntology.ai/paper/2204.01266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01266"}},"official":{"repos":["chongminggao/cirs-codes"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/quantifying-availability-and-discovery-in","slug":"quantifying-availability-and-discovery-in","title":"Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability","date":"2021-06-30","arxiv_id":"2107.00833","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quantifying-availability-and-discovery-in#ran","syntology_url":"https://syntology.ai/paper/2107.00833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00833"}},"official":{"repos":["modestyachts/stochastic-rec-reachability"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-text-based-deep-reinforcement-learning","slug":"a-text-based-deep-reinforcement-learning","title":"A Text-based Deep Reinforcement Learning Framework for Interactive Recommendation","date":"2020-04-14","arxiv_id":"2004.06651","repositories_listed":1,"syntology":null},{"url":"/paper/recsim-a-configurable-simulation-platform-for","slug":"recsim-a-configurable-simulation-platform-for","title":"RecSim: A Configurable Simulation Platform for Recommender Systems","date":"2019-09-11","arxiv_id":"1909.04847","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/recsim-a-configurable-simulation-platform-for#ran","syntology_url":"https://syntology.ai/paper/1909.04847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04847"}},"official":{"repos":["google-research/recsim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/query-based-interactive-recommendation-by","slug":"query-based-interactive-recommendation-by","title":"Query-based Interactive Recommendation by Meta-Path and Adapted Attention-GRU","date":"2019-06-24","arxiv_id":"1907.01639","repositories_listed":1,"syntology":null},{"url":null,"slug":"interarec-interactive-recommendations-using","title":"InteraRec: Screenshot Based Recommendations Using Multimodal Large Language Models","date":"2024-02-26","arxiv_id":"2403.00822","repositories_listed":0,"syntology":null},{"url":null,"slug":"debiased-model-based-interactive","title":"Debiased Model-based Interactive Recommendation","date":"2024-02-24","arxiv_id":"2402.15819","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-neural-causal-model-for-interactive","title":"A General Neural Causal Model for Interactive Recommendation","date":"2023-10-30","arxiv_id":"2310.19519","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-batch-inverse-reinforcement","title":"Adversarial Batch Inverse Reinforcement Learning: Learn to Reward from Imperfect Demonstration for Interactive Recommendation","date":"2023-10-30","arxiv_id":"2310.19536","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-elicitation-with-soft-attributes","title":"Preference Elicitation with Soft Attributes in Interactive Recommendation","date":"2023-10-22","arxiv_id":"2311.02085","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-offline-reinforcement-learning","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","date":"2023-10-01","arxiv_id":"2310.00678","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-validating-long-term-user-feedbacks","title":"Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems","date":"2023-08-22","arxiv_id":"2308.11137","repositories_listed":0,"syntology":null},{"url":null,"slug":"triple-structural-information-modelling-for","title":"Triple Structural Information Modelling for Accurate, Explainable and Interactive Recommendation","date":"2023-04-23","arxiv_id":"2304.11528","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-human-interactive-recommendation","title":"Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning","date":"2022-10-06","arxiv_id":"2210.10638","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-global-sensitivity-for-differentially","title":"Dynamic Global Sensitivity for Differentially Private Contextual Bandits","date":"2022-08-30","arxiv_id":"2208.14555","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-for-interactive","title":"Contrastive Learning for Interactive Recommendation in Fashion","date":"2022-07-25","arxiv_id":"2207.12033","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-agnostic-counterfactual-synthesis","title":"Model-agnostic Counterfactual Synthesis Policy for Interactive Recommendation","date":"2022-04-01","arxiv_id":"2204.00308","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-robustness-of-deep-reinforcement","title":"Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systems","date":"2021-12-02","arxiv_id":"2112.00973","repositories_listed":0,"syntology":null},{"url":null,"slug":"d2rlir-an-improved-and-diversified-ranking","title":"D2RLIR : an improved and diversified ranking function in interactive recommendation systems based on deep reinforcement learning","date":"2021-10-28","arxiv_id":"2110.15089","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-reinforcement-learning-for-1","title":"A Survey on Reinforcement Learning for Recommender Systems","date":"2021-09-22","arxiv_id":"2109.10665","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-use-of-bandit-algorithms-in-intelligent","title":"The Use of Bandit Algorithms in Intelligent Interactive Recommender Systems","date":"2021-07-01","arxiv_id":"2107.00161","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-accuracy-and-fairness-for","title":"Balancing Accuracy and Fairness for Interactive Recommendation with Reinforcement Learning","date":"2021-06-25","arxiv_id":"2106.13386","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-and-whom-to-collaborate-with-in-a","title":"When and Whom to Collaborate with in a Changing Environment: A Collaborative Dynamic Bandit Solution","date":"2021-04-14","arxiv_id":"2104.07150","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-bandit-framework-for-diversified","title":"A Hybrid Bandit Framework for Diversified Recommendation","date":"2020-12-24","arxiv_id":"2012.13245","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-and-detection-on","title":"Adversarial Attacks and Detection on Reinforcement Learning-Based Interactive Recommender Systems","date":"2020-06-14","arxiv_id":"2006.07934","repositories_listed":0,"syntology":null},{"url":null,"slug":"reward-constrained-interactive-recommendation","title":"Reward Constrained Interactive Recommendation with Natural Language Feedback","date":"2020-05-04","arxiv_id":"2005.01618","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-guided-deep-reinforcement-learning","title":"Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation","date":"2020-04-17","arxiv_id":"2004.08068","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-based-interactive-recommendation-via","title":"Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"irf-interactive-recommendation-through","title":"IRF: Interactive Recommendation through Dialogue","date":"2019-10-03","arxiv_id":"1910.03040","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandit-learning-for-diversified-interactive","title":"Bandit Learning for Diversified Interactive Recommendation","date":"2019-07-01","arxiv_id":"1907.01647","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversity-promoting-deep-reinforcement","title":"Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation","date":"2019-03-19","arxiv_id":"1903.07826","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-collaborative-filtering-meets","title":"When Collaborative Filtering Meets Reinforcement Learning","date":"2019-02-02","arxiv_id":"1902.00715","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-interactive-recommendation-with","title":"Large-scale Interactive Recommendation with Tree-structured Policy Gradient","date":"2018-11-14","arxiv_id":"1811.05869","repositories_listed":0,"syntology":null},{"url":null,"slug":"visually-aware-personalized-recommendation","title":"Visually-Aware Personalized Recommendation using Interpretable Image Representations","date":"2018-06-26","arxiv_id":"1806.09820","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-interactive-collaborative-filtering","title":"Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms","date":"2017-08-10","arxiv_id":"1708.03058","repositories_listed":0,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/task/interactive-recommendation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/interactive-recommendation/papers/ran/1","json":"/task/interactive-recommendation/papers/ran/1.json","rows":4}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"cd682eead78eadaebe62ccf7556c52dcd44852c41fe66c160fdb4551ce67595a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}