{"url":"/task/multi-agent-integration","name":"Multi-agent Integration","slug":"multi-agent-integration","description_markdown":null,"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":9,"papers_with_code":7,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":0},"benchmarks":[{"leaderboard":"/sota/multi-agent-integration-on-bbai-dataset","slug":"multi-agent-integration-on-bbai-dataset","dataset":"BBAI Dataset","dataset_url":"/dataset/bbai-dataset","rows_in_archive":1,"metrics":["P@1"],"first_row_in_archive_order":{"model":"MARS Encoder","paper_title":"One Agent To Rule Them All: Towards Multi-agent Conversational AI","paper_url":"/paper/one-agent-to-rule-them-all-towards-multi-1","paper_date":"2022-03-15","arxiv_id":"2203.07665","code_links":[{"title":"ChrisIsKing/black-box-multi-agent-integation","url":"https://github.com/ChrisIsKing/black-box-multi-agent-integation"}],"syntology":null}}],"datasets":[{"url":"/dataset/bbai-dataset","name":"BBAI Dataset","full_name":"Black-box Agent Integration","num_papers_in_archive":1},{"url":"/dataset/llmafia","name":"LLMafia","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":7,"of":7,"tagged_in_all":9,"items":[{"url":"/paper/autonomous-agents-for-collaborative-task","title":"Autonomous Agents for Collaborative Task under Information Asymmetry","date":"2024-06-21","arxiv_id":"2406.14928","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/mitigating-bias-in-queer-representation","title":"Mitigating Bias in Queer Representation within Large Language Models: A Collaborative Agent Approach","date":"2024-11-12","arxiv_id":"2411.07656","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/preflexor-preference-based-recursive-language","title":"PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking","date":"2024-10-16","arxiv_id":"2410.12375","repositories_listed":1,"syntology":null},{"url":"/paper/autodefense-multi-agent-llm-defense-against","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","date":"2024-03-02","arxiv_id":"2403.04783","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/agentscope-a-flexible-yet-robust-multi-agent","title":"AgentScope: A Flexible yet Robust Multi-Agent Platform","date":"2024-02-21","arxiv_id":"2402.14034","repositories_listed":1,"syntology":null},{"url":"/paper/one-agent-to-rule-them-all-towards-multi-1","title":"One Agent To Rule Them All: Towards Multi-agent Conversational AI","date":"2022-03-15","arxiv_id":"2203.07665","repositories_listed":1,"syntology":null},{"url":"/paper/smash-a-semantic-enabled-multi-agent-approach","title":"SMASH: a Semantic-enabled Multi-agent Approach for Self-adaptation of Human-centered IoT","date":"2021-05-31","arxiv_id":"2105.14915","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}