{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TFI4BKQLYNTZZDYMQ73MSYFASF","short_pith_number":"pith:TFI4BKQL","schema_version":"1.0","canonical_sha256":"9951c0aa0bc3679c8f0c87f6c960a0915a1ca5033dfd60a77ba7c9252c0bfbf2","source":{"kind":"arxiv","id":"2406.06613","version":2},"attestation_state":"computed","paper":{"title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anthony Costarelli, Arjun Yadav, Carlson Cheng, Grace Sodunke, Joshua Clymer, Mat Allen, Roman Hauksson, Suhas Hariharan, Wenjie Li","submitted_at":"2024-06-07T00:28:43Z","abstract_excerpt":"Large language models have demonstrated remarkable few-shot performance on many natural language understanding tasks. Despite several demonstrations of using large language models in complex, strategic scenarios, there lacks a comprehensive framework for evaluating agents' performance across various types of reasoning found in games. To address this gap, we introduce GameBench, a cross-domain benchmark for evaluating strategic reasoning abilities of LLM agents. We focus on 9 different game environments, where each covers at least one axis of key reasoning skill identified in strategy games, an"},"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":"2406.06613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T00:28:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f9eca2e477ebd2c137704f8a6499246dbb3f3a976b1934735725ba75b4d2010","abstract_canon_sha256":"1aeaa0cb6707f5fd4d17b1f5b8dc2f8a4b9a2beba0878454239c4dd3ec30dbeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:55.397045Z","signature_b64":"mCRVJ21NkJXMUMpfFgC+6bDyhAvEQIdIZBj0eJagBVYx5R5qG4VUR9bhHX8xsIECqvw/KH0L6ej7N6fleBYGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9951c0aa0bc3679c8f0c87f6c960a0915a1ca5033dfd60a77ba7c9252c0bfbf2","last_reissued_at":"2026-07-05T08:46:55.396538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:55.396538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anthony Costarelli, Arjun Yadav, Carlson Cheng, Grace Sodunke, Joshua Clymer, Mat Allen, Roman Hauksson, Suhas Hariharan, Wenjie Li","submitted_at":"2024-06-07T00:28:43Z","abstract_excerpt":"Large language models have demonstrated remarkable few-shot performance on many natural language understanding tasks. Despite several demonstrations of using large language models in complex, strategic scenarios, there lacks a comprehensive framework for evaluating agents' performance across various types of reasoning found in games. To address this gap, we introduce GameBench, a cross-domain benchmark for evaluating strategic reasoning abilities of LLM agents. We focus on 9 different game environments, where each covers at least one axis of key reasoning skill identified in strategy games, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06613","kind":"arxiv","version":2},"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/2406.06613/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":"2406.06613","created_at":"2026-07-05T08:46:55.396604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06613v2","created_at":"2026-07-05T08:46:55.396604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06613","created_at":"2026-07-05T08:46:55.396604+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFI4BKQLYNTZ","created_at":"2026-07-05T08:46:55.396604+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFI4BKQLYNTZZDYM","created_at":"2026-07-05T08:46:55.396604+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFI4BKQL","created_at":"2026-07-05T08:46:55.396604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24391","citing_title":"Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19308","citing_title":"Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19338","citing_title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27397","citing_title":"SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29512","citing_title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17637","citing_title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23238","citing_title":"GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22238","citing_title":"Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12824","citing_title":"Mechanism Plausibility in Generative Agent-Based Modeling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17637","citing_title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17510","citing_title":"Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance","ref_index":17,"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":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12824","citing_title":"Mechanism Plausibility in Generative Agent-Based Modeling","ref_index":16,"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":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17244","citing_title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF","json":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF.json","graph_json":"https://pith.science/api/pith-number/TFI4BKQLYNTZZDYMQ73MSYFASF/graph.json","events_json":"https://pith.science/api/pith-number/TFI4BKQLYNTZZDYMQ73MSYFASF/events.json","paper":"https://pith.science/paper/TFI4BKQL"},"agent_actions":{"view_html":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF","download_json":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF.json","view_paper":"https://pith.science/paper/TFI4BKQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06613&json=true","fetch_graph":"https://pith.science/api/pith-number/TFI4BKQLYNTZZDYMQ73MSYFASF/graph.json","fetch_events":"https://pith.science/api/pith-number/TFI4BKQLYNTZZDYMQ73MSYFASF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF/action/storage_attestation","attest_author":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF/action/author_attestation","sign_citation":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF/action/citation_signature","submit_replication":"https://pith.science/pith/TFI4BKQLYNTZZDYMQ73MSYFASF/action/replication_record"}},"created_at":"2026-07-05T08:46:55.396604+00:00","updated_at":"2026-07-05T08:46:55.396604+00:00"}