{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4RWVWVFE7MAHVKFY2D6WS5QGLT","short_pith_number":"pith:4RWVWVFE","schema_version":"1.0","canonical_sha256":"e46d5b54a4fb007aa8b8d0fd6976065ce27bbbf1de36b630fddf91bd8c7122c3","source":{"kind":"arxiv","id":"2408.15971","version":1},"attestation_state":"computed","paper":{"title":"BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyan Wang, Dan Zhang, Jie Tang, Tao Feng, Wei Wang","submitted_at":"2024-08-28T17:43:55Z","abstract_excerpt":"Large Language Models (LLMs) are becoming increasingly powerful and capable of handling complex tasks, e.g., building single agents and multi-agent systems. Compared to single agents, multi-agent systems have higher requirements for the collaboration capabilities of language models. Many benchmarks are proposed to evaluate their collaborative abilities. However, these benchmarks lack fine-grained evaluations of LLM collaborative capabilities. Additionally, multi-agent collaborative and competitive scenarios are ignored in existing works. To address these two problems, we propose a benchmark, c"},"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":"2408.15971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T17:43:55Z","cross_cats_sorted":[],"title_canon_sha256":"f825da8cbd705f0ad0533246aab93eaeb9d64024a1152957fb78aee26a4da8c0","abstract_canon_sha256":"751aa01dada819b0e9d96dd954d59ea1bcc0d45e087760c5ead5a94a2684ea57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:20.020144Z","signature_b64":"vO2vjOFLwnm1CI0OpjqcOKiIWCBTJcIV5ncUufSYeRWiCZycxeHBpH+tXLGaQTYfpbQ09WBDIFfjmos6kpvTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e46d5b54a4fb007aa8b8d0fd6976065ce27bbbf1de36b630fddf91bd8c7122c3","last_reissued_at":"2026-07-05T09:00:20.019681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:20.019681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boyan Wang, Dan Zhang, Jie Tang, Tao Feng, Wei Wang","submitted_at":"2024-08-28T17:43:55Z","abstract_excerpt":"Large Language Models (LLMs) are becoming increasingly powerful and capable of handling complex tasks, e.g., building single agents and multi-agent systems. Compared to single agents, multi-agent systems have higher requirements for the collaboration capabilities of language models. Many benchmarks are proposed to evaluate their collaborative abilities. However, these benchmarks lack fine-grained evaluations of LLM collaborative capabilities. Additionally, multi-agent collaborative and competitive scenarios are ignored in existing works. To address these two problems, we propose a benchmark, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15971","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/2408.15971/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":"2408.15971","created_at":"2026-07-05T09:00:20.019732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15971v1","created_at":"2026-07-05T09:00:20.019732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15971","created_at":"2026-07-05T09:00:20.019732+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RWVWVFE7MAH","created_at":"2026-07-05T09:00:20.019732+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RWVWVFE7MAHVKFY","created_at":"2026-07-05T09:00:20.019732+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RWVWVFE","created_at":"2026-07-05T09:00:20.019732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08790","citing_title":"RAILS: Verification-Native Clearing For Agentic Commerce","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08340","citing_title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06399","citing_title":"CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":296,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13172","citing_title":"When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25088","citing_title":"Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07733","citing_title":"CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT","json":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT.json","graph_json":"https://pith.science/api/pith-number/4RWVWVFE7MAHVKFY2D6WS5QGLT/graph.json","events_json":"https://pith.science/api/pith-number/4RWVWVFE7MAHVKFY2D6WS5QGLT/events.json","paper":"https://pith.science/paper/4RWVWVFE"},"agent_actions":{"view_html":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT","download_json":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT.json","view_paper":"https://pith.science/paper/4RWVWVFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15971&json=true","fetch_graph":"https://pith.science/api/pith-number/4RWVWVFE7MAHVKFY2D6WS5QGLT/graph.json","fetch_events":"https://pith.science/api/pith-number/4RWVWVFE7MAHVKFY2D6WS5QGLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT/action/storage_attestation","attest_author":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT/action/author_attestation","sign_citation":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT/action/citation_signature","submit_replication":"https://pith.science/pith/4RWVWVFE7MAHVKFY2D6WS5QGLT/action/replication_record"}},"created_at":"2026-07-05T09:00:20.019732+00:00","updated_at":"2026-07-05T09:00:20.019732+00:00"}