{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U4ID6NJRNXWAHCLLRAKS4T5ZOX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0c97c0d71461757cbc61049490d0950b2ffa952a7ea4cc2424c40fb093deed1d","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T05:18:50Z","title_canon_sha256":"ce39eb13710a9858f5578458f6810b36906857eb3725b8c84ec7eb717b90025b"},"schema_version":"1.0","source":{"id":"2503.01935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01935","created_at":"2026-07-05T10:23:32Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01935v1","created_at":"2026-07-05T10:23:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01935","created_at":"2026-07-05T10:23:32Z"},{"alias_kind":"pith_short_12","alias_value":"U4ID6NJRNXWA","created_at":"2026-07-05T10:23:32Z"},{"alias_kind":"pith_short_16","alias_value":"U4ID6NJRNXWAHCLL","created_at":"2026-07-05T10:23:32Z"},{"alias_kind":"pith_short_8","alias_value":"U4ID6NJR","created_at":"2026-07-05T10:23:32Z"}],"graph_snapshots":[{"event_id":"sha256:d80d22c6edc6216cd69a1a92c976795e8a26f02fa68c40eba48d46593a240aff","target":"graph","created_at":"2026-07-05T10:23:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.01935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition. In this paper, we introduce MultiAgentBench, a comprehensive benchmark designed to evaluate LLM-based multi-agent systems across diverse, interactive scenarios. Our framework measures not only task completion but also the quality of collaboration and competition using novel, milestone-based key performance indicators. Moreover, we evaluate v","authors_text":"Cheng Qian, Heng Ji, Hongyi Du, Jiaxuan You, Kunlun Zhu, Shuyi Guo, Xiangru Tang, Xiaocheng Yang, Zhaochen Hong, Zhenhailong Wang, Zhe Wang","cross_cats":["cs.AI","cs.CL","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T05:18:50Z","title":"MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01935","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d147219cf8def371363e42f19d6db876ead21f1cf9784023dd8a918c92b71673","target":"record","created_at":"2026-07-05T10:23:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0c97c0d71461757cbc61049490d0950b2ffa952a7ea4cc2424c40fb093deed1d","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T05:18:50Z","title_canon_sha256":"ce39eb13710a9858f5578458f6810b36906857eb3725b8c84ec7eb717b90025b"},"schema_version":"1.0","source":{"id":"2503.01935","kind":"arxiv","version":1}},"canonical_sha256":"a7103f35316dec03896b88152e4fb975f897cd9cb80b421a6c67d9d5b8bac513","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7103f35316dec03896b88152e4fb975f897cd9cb80b421a6c67d9d5b8bac513","first_computed_at":"2026-07-05T10:23:32.884895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:32.884895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xwFF8//dnyxbEllOQYHh4sHDqj72Rm2Kcj9YlpHY5yx6A739JXzYh39K4sB+H9sZuvVJR86N8AJs2ppL+uF7Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:32.885510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d147219cf8def371363e42f19d6db876ead21f1cf9784023dd8a918c92b71673","sha256:d80d22c6edc6216cd69a1a92c976795e8a26f02fa68c40eba48d46593a240aff"],"state_sha256":"6ab2ee5e047e094232a214358d93793fba8c8d6b95e737f7d7a4704ebda9b907"}