{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GHY7YA2HMG7IU2OA6SSNDC4QMD","short_pith_number":"pith:GHY7YA2H","schema_version":"1.0","canonical_sha256":"31f1fc034761be8a69c0f4a4d18b9060fb4da61e20aee1a58992d17d6e03d5ea","source":{"kind":"arxiv","id":"2607.21013","version":1},"attestation_state":"computed","paper":{"title":"EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Jinghui Qin, kebin Jin, Lihuang Fang, Yuchen Zou","submitted_at":"2026-07-23T07:52:40Z","abstract_excerpt":"Multimodal large language models (MLLMs) have achieved impressive performance in multimodal emotion recognition (MER) tasks and lifted MER to a new level that is complex emotion understanding with advanced video understanding abilities and natural language description. However, existing MLLM-based methods often use a fixed prompt to perceive the emotions, ignoring the dynamicity and complexity of the emotion source in the multimodal inputs. To address these issues, we propose a novel Reinforcement Learning-based Dynamic Agent Specialization framework (\\textbf{EmoAgent-R1}) to optimize the emot"},"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":"2607.21013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T07:52:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4ca9074316cd43a133ebf393671745d98e58d93ed5adcb027d31b88cf1a0a601","abstract_canon_sha256":"0d474538aaffffd254816246d041eeca947dae6164b440529b388c5dfeaf2ba8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:47.415561Z","signature_b64":"8JIpOx7QbU7khvMGfzAke8jEx4n7ipZSjwrVDGbgj0Jz4VUo61A7AJNm9Dzn0aFbA7vUkGY2KXR+TBw/53bQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31f1fc034761be8a69c0f4a4d18b9060fb4da61e20aee1a58992d17d6e03d5ea","last_reissued_at":"2026-07-24T01:23:47.414670Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:47.414670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Jinghui Qin, kebin Jin, Lihuang Fang, Yuchen Zou","submitted_at":"2026-07-23T07:52:40Z","abstract_excerpt":"Multimodal large language models (MLLMs) have achieved impressive performance in multimodal emotion recognition (MER) tasks and lifted MER to a new level that is complex emotion understanding with advanced video understanding abilities and natural language description. However, existing MLLM-based methods often use a fixed prompt to perceive the emotions, ignoring the dynamicity and complexity of the emotion source in the multimodal inputs. To address these issues, we propose a novel Reinforcement Learning-based Dynamic Agent Specialization framework (\\textbf{EmoAgent-R1}) to optimize the emot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21013","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/2607.21013/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":"2607.21013","created_at":"2026-07-24T01:23:47.415129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21013v1","created_at":"2026-07-24T01:23:47.415129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21013","created_at":"2026-07-24T01:23:47.415129+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHY7YA2HMG7I","created_at":"2026-07-24T01:23:47.415129+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHY7YA2HMG7IU2OA","created_at":"2026-07-24T01:23:47.415129+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHY7YA2H","created_at":"2026-07-24T01:23:47.415129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD","json":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD.json","graph_json":"https://pith.science/api/pith-number/GHY7YA2HMG7IU2OA6SSNDC4QMD/graph.json","events_json":"https://pith.science/api/pith-number/GHY7YA2HMG7IU2OA6SSNDC4QMD/events.json","paper":"https://pith.science/paper/GHY7YA2H"},"agent_actions":{"view_html":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD","download_json":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD.json","view_paper":"https://pith.science/paper/GHY7YA2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21013&json=true","fetch_graph":"https://pith.science/api/pith-number/GHY7YA2HMG7IU2OA6SSNDC4QMD/graph.json","fetch_events":"https://pith.science/api/pith-number/GHY7YA2HMG7IU2OA6SSNDC4QMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD/action/storage_attestation","attest_author":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD/action/author_attestation","sign_citation":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD/action/citation_signature","submit_replication":"https://pith.science/pith/GHY7YA2HMG7IU2OA6SSNDC4QMD/action/replication_record"}},"created_at":"2026-07-24T01:23:47.415129+00:00","updated_at":"2026-07-24T01:23:47.415129+00:00"}