{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UKR4GJ33FY7NHK7MFTFHLNL4PY","short_pith_number":"pith:UKR4GJ33","schema_version":"1.0","canonical_sha256":"a2a3c3277b2e3ed3abec2cca75b57c7e0500dd7d0713aaaf76ce008ccc4dd2b6","source":{"kind":"arxiv","id":"2606.05793","version":1},"attestation_state":"computed","paper":{"title":"CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aimin Zhou, Hanjie Ge, Haotian Shi, Hong Qian, Jingwen Yang, Liang Dou, Xiangfeng Wang, Yuanhao Liu, Zihan Zhou, Zongbao Zhang","submitted_at":"2026-06-04T07:22:44Z","abstract_excerpt":"While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative studies lack grounded interaction and behavioral execution, motivating the need for cooperative game environments that enable contextualized and immersive collaboration. To this end, this paper proposes CollabBench, a benchmark for evaluating and training collaborative agents in cooperative games. CollabBench features a Diverse Player Profile Simulation pipeline to model varied players behaviors, and a Collaborative A"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.05793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T07:22:44Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"6b3736744bd8bc286745842e717f54308964b45303b38c24fca425bdcb2ca2f6","abstract_canon_sha256":"fcea3918e568bc5e277c743d2645ec698a0ee5b620c1c276843ff115bba36f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:03.520847Z","signature_b64":"66hqXduoT4h4pcSsYJAPHUPFA/6Nl7gugeIeKuavOCArjE5ul2Ae3yOWccSsWFXDNp6I9IYPWb5V0yD2psZ2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2a3c3277b2e3ed3abec2cca75b57c7e0500dd7d0713aaaf76ce008ccc4dd2b6","last_reissued_at":"2026-06-05T01:15:03.520337Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:03.520337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aimin Zhou, Hanjie Ge, Haotian Shi, Hong Qian, Jingwen Yang, Liang Dou, Xiangfeng Wang, Yuanhao Liu, Zihan Zhou, Zongbao Zhang","submitted_at":"2026-06-04T07:22:44Z","abstract_excerpt":"While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative studies lack grounded interaction and behavioral execution, motivating the need for cooperative game environments that enable contextualized and immersive collaboration. To this end, this paper proposes CollabBench, a benchmark for evaluating and training collaborative agents in cooperative games. CollabBench features a Diverse Player Profile Simulation pipeline to model varied players behaviors, and a Collaborative A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05793","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.05793/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.05793","created_at":"2026-06-05T01:15:03.520433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05793v1","created_at":"2026-06-05T01:15:03.520433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05793","created_at":"2026-06-05T01:15:03.520433+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKR4GJ33FY7N","created_at":"2026-06-05T01:15:03.520433+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKR4GJ33FY7NHK7M","created_at":"2026-06-05T01:15:03.520433+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKR4GJ33","created_at":"2026-06-05T01:15:03.520433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY","json":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY.json","graph_json":"https://pith.science/api/pith-number/UKR4GJ33FY7NHK7MFTFHLNL4PY/graph.json","events_json":"https://pith.science/api/pith-number/UKR4GJ33FY7NHK7MFTFHLNL4PY/events.json","paper":"https://pith.science/paper/UKR4GJ33"},"agent_actions":{"view_html":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY","download_json":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY.json","view_paper":"https://pith.science/paper/UKR4GJ33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05793&json=true","fetch_graph":"https://pith.science/api/pith-number/UKR4GJ33FY7NHK7MFTFHLNL4PY/graph.json","fetch_events":"https://pith.science/api/pith-number/UKR4GJ33FY7NHK7MFTFHLNL4PY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY/action/storage_attestation","attest_author":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY/action/author_attestation","sign_citation":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY/action/citation_signature","submit_replication":"https://pith.science/pith/UKR4GJ33FY7NHK7MFTFHLNL4PY/action/replication_record"}},"created_at":"2026-06-05T01:15:03.520433+00:00","updated_at":"2026-06-05T01:15:03.520433+00:00"}