{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QSFG7ET7Y7ISV2PF3WBOH5Z5EM","short_pith_number":"pith:QSFG7ET7","schema_version":"1.0","canonical_sha256":"848a6f927fc7d12ae9e5dd82e3f73d23208af2787243964d08d815aed6e7b09d","source":{"kind":"arxiv","id":"2407.07086","version":2},"attestation_state":"computed","paper":{"title":"Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Agam Bhatia, Daniel LK Yamins, Logan Cross, Nick Haber, Violet Xiang","submitted_at":"2024-07-09T17:57:15Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) methods struggle with the non-stationarity of multi-agent systems and fail to adaptively learn online when tested with novel agents. Here, we leverage large language models (LLMs) to create an autonomous agent that can handle these challenges. Our agent, Hypothetical Minds, consists of a cognitively-inspired architecture, featuring modular components for perception, memory, and hierarchical planning over two levels of abstraction. We introduce the Theory of Mind module that scaffolds the high-level planning process by generating hypotheses about other "},"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":"2407.07086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-09T17:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"f3998ff955ef0ef25d6d22810c43f8af37077d7fabc106c7d20af7a5ed7fd6be","abstract_canon_sha256":"f29d77c2c6a5b0dadf91b0f53ba3ca92dbb946b5922ac76868acb7eb68b69829"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:55.750669Z","signature_b64":"F8/QGZ6PE+u+PbWdjeDsGcFTjGNdSayX90fGTx7tM5TwrfBuCCxzM7+t5EsGu+O4nKiIWNpbKh1WlFJ8GI/NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"848a6f927fc7d12ae9e5dd82e3f73d23208af2787243964d08d815aed6e7b09d","last_reissued_at":"2026-07-05T09:47:55.750285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:55.750285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Agam Bhatia, Daniel LK Yamins, Logan Cross, Nick Haber, Violet Xiang","submitted_at":"2024-07-09T17:57:15Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) methods struggle with the non-stationarity of multi-agent systems and fail to adaptively learn online when tested with novel agents. Here, we leverage large language models (LLMs) to create an autonomous agent that can handle these challenges. Our agent, Hypothetical Minds, consists of a cognitively-inspired architecture, featuring modular components for perception, memory, and hierarchical planning over two levels of abstraction. We introduce the Theory of Mind module that scaffolds the high-level planning process by generating hypotheses about other "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07086","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/2407.07086/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":"2407.07086","created_at":"2026-07-05T09:47:55.750344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07086v2","created_at":"2026-07-05T09:47:55.750344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07086","created_at":"2026-07-05T09:47:55.750344+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSFG7ET7Y7IS","created_at":"2026-07-05T09:47:55.750344+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSFG7ET7Y7ISV2PF","created_at":"2026-07-05T09:47:55.750344+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSFG7ET7","created_at":"2026-07-05T09:47:55.750344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19308","citing_title":"Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00240","citing_title":"MindZero: Learning Online Mental Reasoning With Zero Annotations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27593","citing_title":"Voluntary Collusion with Secret Tools in Competing LLM Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22602","citing_title":"Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents","ref_index":36,"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":279,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00487","citing_title":"Competition and Cooperation of LLM Agents in Games","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM","json":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM.json","graph_json":"https://pith.science/api/pith-number/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/graph.json","events_json":"https://pith.science/api/pith-number/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/events.json","paper":"https://pith.science/paper/QSFG7ET7"},"agent_actions":{"view_html":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM","download_json":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM.json","view_paper":"https://pith.science/paper/QSFG7ET7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07086&json=true","fetch_graph":"https://pith.science/api/pith-number/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/graph.json","fetch_events":"https://pith.science/api/pith-number/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/action/storage_attestation","attest_author":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/action/author_attestation","sign_citation":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/action/citation_signature","submit_replication":"https://pith.science/pith/QSFG7ET7Y7ISV2PF3WBOH5Z5EM/action/replication_record"}},"created_at":"2026-07-05T09:47:55.750344+00:00","updated_at":"2026-07-05T09:47:55.750344+00:00"}