{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VYEGCBLOU7V3NPZRRSKMM2Z4CO","short_pith_number":"pith:VYEGCBLO","schema_version":"1.0","canonical_sha256":"ae0861056ea7ebb6bf318c94c66b3c13a3c05609daf6d33f2c1c7bae7f286f28","source":{"kind":"arxiv","id":"2608.05832","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Ju, Dexin Kong, Fei Huang, Jufeng Chen, Kakam Chong, Qingyuan Tian, Rui Wang, Shuai Xiao, Shuai Zhao, Shuguang Han, Xiaofeng Wang, Xu Yan","submitted_at":"2026-08-06T10:00:50Z","abstract_excerpt":"Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination and rapid adaptation. Current methods often apply uniform goal-based rewards to every utterance, overlooking the specificity of objectives at each dialogue turn and failing to account for the rationale of potential strategies. Inspired by the Theory of Planned Behavior, we propose the Think-Strategy-Response (TSR) framework, which decomposes social dialogue into two hierarchical stages: high-level strategic planning and low-level linguistic ex"},"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":"2608.05832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T10:00:50Z","cross_cats_sorted":[],"title_canon_sha256":"7d4636b9df676e847c7106eb464c49f5197a8ab5e709097287ee40573ce9ff87","abstract_canon_sha256":"bbb87c68c6d5bd1e5cdfdc44b825f0f2aef3c6d8e80999d6e9fa57d4fce7e4e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:51.124469Z","signature_b64":"8tGF78fPk7vLdtuQ4mBDbIVZlsFUfiAn2vadShKmvUG00GDgjIjeCv9upySOwEtnb4NAC5f1Q9DYb6jPs5kDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae0861056ea7ebb6bf318c94c66b3c13a3c05609daf6d33f2c1c7bae7f286f28","last_reissued_at":"2026-08-07T00:52:51.123044Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:51.123044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Ju, Dexin Kong, Fei Huang, Jufeng Chen, Kakam Chong, Qingyuan Tian, Rui Wang, Shuai Xiao, Shuai Zhao, Shuguang Han, Xiaofeng Wang, Xu Yan","submitted_at":"2026-08-06T10:00:50Z","abstract_excerpt":"Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination and rapid adaptation. Current methods often apply uniform goal-based rewards to every utterance, overlooking the specificity of objectives at each dialogue turn and failing to account for the rationale of potential strategies. Inspired by the Theory of Planned Behavior, we propose the Think-Strategy-Response (TSR) framework, which decomposes social dialogue into two hierarchical stages: high-level strategic planning and low-level linguistic ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05832","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/2608.05832/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":"2608.05832","created_at":"2026-08-07T00:52:51.124590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05832v1","created_at":"2026-08-07T00:52:51.124590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05832","created_at":"2026-08-07T00:52:51.124590+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYEGCBLOU7V3","created_at":"2026-08-07T00:52:51.124590+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYEGCBLOU7V3NPZR","created_at":"2026-08-07T00:52:51.124590+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYEGCBLO","created_at":"2026-08-07T00:52:51.124590+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/VYEGCBLOU7V3NPZRRSKMM2Z4CO","json":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO.json","graph_json":"https://pith.science/api/pith-number/VYEGCBLOU7V3NPZRRSKMM2Z4CO/graph.json","events_json":"https://pith.science/api/pith-number/VYEGCBLOU7V3NPZRRSKMM2Z4CO/events.json","paper":"https://pith.science/paper/VYEGCBLO"},"agent_actions":{"view_html":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO","download_json":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO.json","view_paper":"https://pith.science/paper/VYEGCBLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05832&json=true","fetch_graph":"https://pith.science/api/pith-number/VYEGCBLOU7V3NPZRRSKMM2Z4CO/graph.json","fetch_events":"https://pith.science/api/pith-number/VYEGCBLOU7V3NPZRRSKMM2Z4CO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO/action/storage_attestation","attest_author":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO/action/author_attestation","sign_citation":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO/action/citation_signature","submit_replication":"https://pith.science/pith/VYEGCBLOU7V3NPZRRSKMM2Z4CO/action/replication_record"}},"created_at":"2026-08-07T00:52:51.124590+00:00","updated_at":"2026-08-07T00:52:51.124590+00:00"}