{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4VWDYPCPTOCPJDN7BDPL6MMRJO","short_pith_number":"pith:4VWDYPCP","schema_version":"1.0","canonical_sha256":"e56c3c3c4f9b84f48dbf08debf31914bac18c7e08295e780363ef404ba19dc52","source":{"kind":"arxiv","id":"2403.11807","version":7},"attestation_state":"computed","paper":{"title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Eric John Li, Jen-tse Huang, Man Ho Lam, Michael R. Lyu, Tian Liang, Wenxiang Jiao, Wenxuan Wang, Xing Wang, Youliang Yuan, Zhaopeng Tu","submitted_at":"2024-03-18T14:04:47Z","abstract_excerpt":"Decision-making is a complex process requiring diverse abilities, making it an excellent framework for evaluating Large Language Models (LLMs). Researchers have examined LLMs' decision-making through the lens of Game Theory. However, existing evaluation mainly focus on two-player scenarios where an LLM competes against another. Additionally, previous benchmarks suffer from test set leakage due to their static design. We introduce GAMA($\\gamma$)-Bench, a new framework for evaluating LLMs' Gaming Ability in Multi-Agent environments. It includes eight classical game theory scenarios and a dynamic"},"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":"2403.11807","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-18T14:04:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1859a9394e223fd572cc8c3e05e80ddef2e449f8272bf8b9c5c7fdb52d3707b4","abstract_canon_sha256":"70abbeded872f4c50a4f0773935942fe635b90a92093e542387586d004277198"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:05.321295Z","signature_b64":"Wf9RlkfuYbthhpbx8HrX096TYNdmrvY0wjNqndAypRWxja5wlqjW0qe7umV9y3wreMAwlNdpzRM65tt7IYtMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56c3c3c4f9b84f48dbf08debf31914bac18c7e08295e780363ef404ba19dc52","last_reissued_at":"2026-07-05T10:25:05.320815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:05.320815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Eric John Li, Jen-tse Huang, Man Ho Lam, Michael R. Lyu, Tian Liang, Wenxiang Jiao, Wenxuan Wang, Xing Wang, Youliang Yuan, Zhaopeng Tu","submitted_at":"2024-03-18T14:04:47Z","abstract_excerpt":"Decision-making is a complex process requiring diverse abilities, making it an excellent framework for evaluating Large Language Models (LLMs). Researchers have examined LLMs' decision-making through the lens of Game Theory. However, existing evaluation mainly focus on two-player scenarios where an LLM competes against another. Additionally, previous benchmarks suffer from test set leakage due to their static design. We introduce GAMA($\\gamma$)-Bench, a new framework for evaluating LLMs' Gaming Ability in Multi-Agent environments. It includes eight classical game theory scenarios and a dynamic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11807","kind":"arxiv","version":7},"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/2403.11807/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":"2403.11807","created_at":"2026-07-05T10:25:05.320873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11807v7","created_at":"2026-07-05T10:25:05.320873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11807","created_at":"2026-07-05T10:25:05.320873+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VWDYPCPTOCP","created_at":"2026-07-05T10:25:05.320873+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VWDYPCPTOCPJDN7","created_at":"2026-07-05T10:25:05.320873+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VWDYPCP","created_at":"2026-07-05T10:25:05.320873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09826","citing_title":"OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04202","citing_title":"SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10521","citing_title":"MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03610","citing_title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10102","citing_title":"When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13875","citing_title":"Common-agency Games for Multi-Objective Test-Time Alignment","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":288,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19260","citing_title":"Understanding the Mechanism of Altruism in Large Language Models","ref_index":251,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO","json":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO.json","graph_json":"https://pith.science/api/pith-number/4VWDYPCPTOCPJDN7BDPL6MMRJO/graph.json","events_json":"https://pith.science/api/pith-number/4VWDYPCPTOCPJDN7BDPL6MMRJO/events.json","paper":"https://pith.science/paper/4VWDYPCP"},"agent_actions":{"view_html":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO","download_json":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO.json","view_paper":"https://pith.science/paper/4VWDYPCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11807&json=true","fetch_graph":"https://pith.science/api/pith-number/4VWDYPCPTOCPJDN7BDPL6MMRJO/graph.json","fetch_events":"https://pith.science/api/pith-number/4VWDYPCPTOCPJDN7BDPL6MMRJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO/action/storage_attestation","attest_author":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO/action/author_attestation","sign_citation":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO/action/citation_signature","submit_replication":"https://pith.science/pith/4VWDYPCPTOCPJDN7BDPL6MMRJO/action/replication_record"}},"created_at":"2026-07-05T10:25:05.320873+00:00","updated_at":"2026-07-05T10:25:05.320873+00:00"}