{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FEU2FJBS77GTFPJALA6GGHYNLC","short_pith_number":"pith:FEU2FJBS","schema_version":"1.0","canonical_sha256":"2929a2a432ffcd32bd20583c631f0d58b6ec6cbad0c60d8f639621d28f3dbf50","source":{"kind":"arxiv","id":"2509.04343","version":1},"attestation_state":"computed","paper":{"title":"Psychologically Enhanced AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.HC","cs.MA"],"primary_cat":"cs.AI","authors_text":"Hubert Niewiadomski, J\\\"urgen M\\\"uller, Maciej Besta, Marcin Chrapek, Mathis Lindner, Patrick Iff, Piotr Nyczyk, Robert Gerstenberger, Sebastian Hermann Martschat, Shriram Chandran, Taraneh Ghandi, Torsten Hoefler","submitted_at":"2025-09-04T16:03:03Z","abstract_excerpt":"We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically"},"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":"2509.04343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-04T16:03:03Z","cross_cats_sorted":["cs.CL","cs.CY","cs.HC","cs.MA"],"title_canon_sha256":"d0020f0a24c84c0765bba80e1dc91026146b4fd071dd659029ebc9c6a73a8cff","abstract_canon_sha256":"6ba5dad9828038054823cfc17e54484498da558b0cc7c2e892513c9b2541ea93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:57.810817Z","signature_b64":"GbxE0976osGP8iqSZQbwaOna7odC0sodqCcKWNEcBAuKGjOk1fWt2DpUO4ndJ6hJ9blbDWDphBGkEkh2PY3xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2929a2a432ffcd32bd20583c631f0d58b6ec6cbad0c60d8f639621d28f3dbf50","last_reissued_at":"2026-07-05T12:04:57.810307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:57.810307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Psychologically Enhanced AI Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.HC","cs.MA"],"primary_cat":"cs.AI","authors_text":"Hubert Niewiadomski, J\\\"urgen M\\\"uller, Maciej Besta, Marcin Chrapek, Mathis Lindner, Patrick Iff, Piotr Nyczyk, Robert Gerstenberger, Sebastian Hermann Martschat, Shriram Chandran, Taraneh Ghandi, Torsten Hoefler","submitted_at":"2025-09-04T16:03:03Z","abstract_excerpt":"We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04343","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/2509.04343/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":"2509.04343","created_at":"2026-07-05T12:04:57.810381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04343v1","created_at":"2026-07-05T12:04:57.810381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04343","created_at":"2026-07-05T12:04:57.810381+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEU2FJBS77GT","created_at":"2026-07-05T12:04:57.810381+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEU2FJBS77GTFPJA","created_at":"2026-07-05T12:04:57.810381+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEU2FJBS","created_at":"2026-07-05T12:04:57.810381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12057","citing_title":"ChargeBD: Character-Aware Heterogeneous Agent Reasoning for Guided Engineering in Battery Development","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21783","citing_title":"NetworkGames: Simulating Cooperation in Network Games with Personality-driven LLM Agents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC","json":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC.json","graph_json":"https://pith.science/api/pith-number/FEU2FJBS77GTFPJALA6GGHYNLC/graph.json","events_json":"https://pith.science/api/pith-number/FEU2FJBS77GTFPJALA6GGHYNLC/events.json","paper":"https://pith.science/paper/FEU2FJBS"},"agent_actions":{"view_html":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC","download_json":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC.json","view_paper":"https://pith.science/paper/FEU2FJBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04343&json=true","fetch_graph":"https://pith.science/api/pith-number/FEU2FJBS77GTFPJALA6GGHYNLC/graph.json","fetch_events":"https://pith.science/api/pith-number/FEU2FJBS77GTFPJALA6GGHYNLC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC/action/storage_attestation","attest_author":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC/action/author_attestation","sign_citation":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC/action/citation_signature","submit_replication":"https://pith.science/pith/FEU2FJBS77GTFPJALA6GGHYNLC/action/replication_record"}},"created_at":"2026-07-05T12:04:57.810381+00:00","updated_at":"2026-07-05T12:04:57.810381+00:00"}