{"entities":{"Q7367870":{"pageid":31550426,"ns":120,"title":"Item:Q7367870","lastrevid":105351500,"modified":"2026-10-07T01:44:45Z","type":"item","id":"Q7367870","labels":{"en":{"language":"en","value":"MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability"}},"descriptions":{},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"fd5912e4dab4b881a8eb0eb27e7893fef55176ad","datavalue":{"value":{"entity-type":"item","numeric-id":56887,"id":"Q56887"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7367870$CAAC2597-74C3-48FC-89DA-44EFA9099614","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7367870$1B48F757-FE62-449A-8D8B-ADFB9C59F247","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"f30a35d16184fc9c44dece34b4a69dd9e210badd","datavalue":{"value":"2610.04672","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7367870$D2F28538-1317-4600-A55B-1CEC43FE8010","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"d0cb0a95f141e6d84b183b2fa4311b6b447c460c","datavalue":{"value":"10.48550/arXiv.2610.04672","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7367870$C1AD98DD-B8CE-40F5-809B-C809FB065D3D","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"b75d46215f33cd2c280731bc8c04073e53eae49e","datavalue":{"value":{"text":"MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q7367870$28770ACE-4669-4A6B-B8F1-6C9C2F666020","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"4e342add91ce916825d24f5b30be53f8b980be0c","datavalue":{"value":{"time":"+2026-10-03T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q7367870$7C1969C2-1985-48AD-9AFF-CF345D40BE44","rank":"normal"}],"P22":[{"mainsnak":{"snaktype":"value","property":"P22","hash":"614924768b75c995c88a0e54bf3be36427e60707","datavalue":{"value":"cs.AI","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$DDB4BBF4-71A8-4587-BD89-1B0F798CE3D6","rank":"normal"}],"P43":[{"mainsnak":{"snaktype":"value","property":"P43","hash":"a3d14794f3e8cd930ad78de8e093083410173cca","datavalue":{"value":"Qizhi Chu","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$DE41F2F2-DA2D-4320-AEA3-F376D82A7407","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"9c6d225244f5f469e78bdab44f9fb6d2e0870aeb","datavalue":{"value":"Zekai Yu","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$430F75D8-C041-464E-8EA8-E4C9C1C9B6A0","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"b77a90008545dde45f2348afd6520da8fe3c616e","datavalue":{"value":"Sijie Wen","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$D24A74EB-23C9-4B72-B88D-3B92B4F533B5","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"a4dbe7db2c3617b048da28a957e37ad20813aea5","datavalue":{"value":"Yang Liu","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$1BD4206D-B537-4FD8-A902-E9A6EBD39260","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"4bb6f66c79f029403f2e5532de4ebbb379dd9e0f","datavalue":{"value":"Chen Qian","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$BA1E2121-A81F-4240-AF05-35A947775DF0","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"a613999fe40df02adc6a51ea67c3477fe2661cd3","datavalue":{"value":"Cheng Yang","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$237198DE-5CB2-4BED-B006-24EE8059255B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"c6bad3c78b2a72f4acd86bcb511aeb1c03e6bf33","datavalue":{"value":"Chuan Shi","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$EE740E9F-1A10-4E84-951E-8EA678D1F6B6","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"b1f5a1a1f15c22e712c014b09cc973c233cc0175","datavalue":{"value":"Zhiyuan Liu","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$49C7546C-8B4F-4A5C-AD19-15A83182B38E","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"0f01a97c28e30e991b493759727ec29485e2764c","datavalue":{"value":{"entity-type":"item","numeric-id":6453766,"id":"Q6453766"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1642":[{"snaktype":"value","property":"P1642","hash":"a54a2b64f7b8568892d0e11c5b15bda62f19839d","datavalue":{"value":{"entity-type":"item","numeric-id":7270033,"id":"Q7270033"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1642"],"id":"Q7367870$E54540C2-1F84-4ABF-A54B-E11F3C3FC26F","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"5ef5c8e22178ae008c75fe098c42d1fbf251b23b","datavalue":{"value":{"entity-type":"item","numeric-id":1665526,"id":"Q1665526"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1642":[{"snaktype":"value","property":"P1642","hash":"a54a2b64f7b8568892d0e11c5b15bda62f19839d","datavalue":{"value":{"entity-type":"item","numeric-id":7270033,"id":"Q7270033"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1642"],"id":"Q7367870$5DF18674-6EEE-43BE-B72F-A56A263ED86D","rank":"normal"}],"P1963":[{"mainsnak":{"snaktype":"value","property":"P1963","hash":"f965a5b2b513d678a27711c72396062f6e97d50c","datavalue":{"value":"We introduce MASBench, a multi-agent collaboration benchmark designed under partially observable constraints to systematically evaluate collaboration mechanisms in Large Language Model (LLM)-based Multi-Agent Systems (MAS). It consists of three task categories and provides deterministic evaluation metrics for collaboration outcomes and communication overhead.","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P1642":[{"snaktype":"value","property":"P1642","hash":"985dbb0e3957a205973fd95bd3fd79ca0980eb5b","datavalue":{"value":{"entity-type":"item","numeric-id":7269921,"id":"Q7269921"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1642"],"id":"Q7367870$0F68E15A-9BA8-4CE8-8D7F-BDEAD954BD04","rank":"normal"}],"P1964":[{"mainsnak":{"snaktype":"value","property":"P1964","hash":"1167194b5b7ae633a40175b92c78fb951edfd637","datavalue":{"value":"LLM-based Multi-Agent Collaboration","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$0F40D236-1A7D-475A-BBE1-2BD00B73426B","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1964","hash":"a8d9b3a922ab23cccdbd97a248adc8f75e15eab3","datavalue":{"value":"Partial Observability","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$9BBC6E4A-DDE0-44DA-8BF4-E394A9EC7D2C","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1964","hash":"1c7ba66550237b22aff2873357b1976990c0ae6d","datavalue":{"value":"Multi-Agent Benchmark","type":"string"},"datatype":"string"},"type":"statement","id":"Q7367870$6D50A4DA-DD00-4783-A65A-2404A669FBD4","rank":"normal"}],"P1642":[{"mainsnak":{"snaktype":"value","property":"P1642","hash":"a54a2b64f7b8568892d0e11c5b15bda62f19839d","datavalue":{"value":{"entity-type":"item","numeric-id":7270033,"id":"Q7270033"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7367870$CFD88958-7620-40C1-A828-BDA048CCF274","rank":"normal"}],"P223":[{"mainsnak":{"snaktype":"value","property":"P223","hash":"3c23a63f6e3e7d91870cbc6a28c439197f880d14","datavalue":{"value":{"entity-type":"item","numeric-id":2959083,"id":"Q2959083"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7367870$DA875AE3-6F57-4050-B3DE-13DEA8173813","rank":"normal","references":[{"hash":"00a86a798f921dd4253b583f01939ca603a79fcd","snaks":{"P98":[{"snaktype":"value","property":"P98","hash":"c23407ba7a179b53a211cae6aa5a1777a222085b","datavalue":{"value":{"entity-type":"item","numeric-id":56440,"id":"Q56440"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"snaks-order":["P98"]}]},{"mainsnak":{"snaktype":"value","property":"P223","hash":"04005c98888bc062dd1e2a5e241e8d111ef51adc","datavalue":{"value":{"entity-type":"item","numeric-id":5704111,"id":"Q5704111"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7367870$88A08F9C-A67E-45DD-9B21-71E5278E52BC","rank":"normal","references":[{"hash":"00a86a798f921dd4253b583f01939ca603a79fcd","snaks":{"P98":[{"snaktype":"value","property":"P98","hash":"c23407ba7a179b53a211cae6aa5a1777a222085b","datavalue":{"value":{"entity-type":"item","numeric-id":56440,"id":"Q56440"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"snaks-order":["P98"]}]},{"mainsnak":{"snaktype":"value","property":"P223","hash":"4d96655518aafee3a6d430454ae375c61bc1f149","datavalue":{"value":{"entity-type":"item","numeric-id":6033011,"id":"Q6033011"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7367870$1912F331-A4FD-41EB-BB79-C008D44A34C2","rank":"normal","references":[{"hash":"00a86a798f921dd4253b583f01939ca603a79fcd","snaks":{"P98":[{"snaktype":"value","property":"P98","hash":"c23407ba7a179b53a211cae6aa5a1777a222085b","datavalue":{"value":{"entity-type":"item","numeric-id":56440,"id":"Q56440"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"snaks-order":["P98"]}]},{"mainsnak":{"snaktype":"value","property":"P223","hash":"8d5aab96dcb7ee51f70a247239d3d82ec85dcdd7","datavalue":{"value":{"entity-type":"item","numeric-id":58167,"id":"Q58167"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7367870$0255F3F5-30F2-4437-9228-7D20E44E3D26","rank":"normal","references":[{"hash":"00a86a798f921dd4253b583f01939ca603a79fcd","snaks":{"P98":[{"snaktype":"value","property":"P98","hash":"c23407ba7a179b53a211cae6aa5a1777a222085b","datavalue":{"value":{"entity-type":"item","numeric-id":56440,"id":"Q56440"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"snaks-order":["P98"]}]}]},"sitelinks":{"mardi":{"site":"mardi","title":"MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/MASBench:_Benchmarking_LLM-based_Multi-Agent_Collaboration_under_Partial_Observability"}}}}}