{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XXFUX44HA2HYO4C37RVEFYGCWC","short_pith_number":"pith:XXFUX44H","schema_version":"1.0","canonical_sha256":"bdcb4bf387068f87705bfc6a42e0c2b0b3427164274efc5ceaef966964a9ee96","source":{"kind":"arxiv","id":"2409.17433","version":1},"attestation_state":"computed","paper":{"title":"HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Haitao Mi, Wenlin Yao","submitted_at":"2024-09-25T23:52:17Z","abstract_excerpt":"Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited. To address this, we propose a novel framework HDFlow for complex reasoning with LLMs that combines fast and slow thinking modes in an adaptive manner. Our approach consists of two key components: 1) a new approach for slow, deliberate reasoning called Dynamic Workflow, which automatically decomposes complex problems into more manageable sub-tasks and dynamically designs a workflow to assemble specialized LLM or"},"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":"2409.17433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T23:52:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4272698dacaa592094c23809f4bcce31107ceabf17ad5cf28eab5f42e155424d","abstract_canon_sha256":"18846b10f3d55207b12292ca7b101f7e432108742556e44ecea73c198515a0fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:53.855008Z","signature_b64":"rkYNe1eQryTmkRpmSM8QhgP7eD3uGL8jFan9T4BgF2S+voT0stvkoouF82hqripsmVplnYiC3TkVmadFxrpRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdcb4bf387068f87705bfc6a42e0c2b0b3427164274efc5ceaef966964a9ee96","last_reissued_at":"2026-07-05T09:11:53.854551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:53.854551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Haitao Mi, Wenlin Yao","submitted_at":"2024-09-25T23:52:17Z","abstract_excerpt":"Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited. To address this, we propose a novel framework HDFlow for complex reasoning with LLMs that combines fast and slow thinking modes in an adaptive manner. Our approach consists of two key components: 1) a new approach for slow, deliberate reasoning called Dynamic Workflow, which automatically decomposes complex problems into more manageable sub-tasks and dynamically designs a workflow to assemble specialized LLM or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17433","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/2409.17433/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":"2409.17433","created_at":"2026-07-05T09:11:53.854606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17433v1","created_at":"2026-07-05T09:11:53.854606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17433","created_at":"2026-07-05T09:11:53.854606+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXFUX44HA2HY","created_at":"2026-07-05T09:11:53.854606+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXFUX44HA2HYO4C3","created_at":"2026-07-05T09:11:53.854606+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXFUX44H","created_at":"2026-07-05T09:11:53.854606+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/XXFUX44HA2HYO4C37RVEFYGCWC","json":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC.json","graph_json":"https://pith.science/api/pith-number/XXFUX44HA2HYO4C37RVEFYGCWC/graph.json","events_json":"https://pith.science/api/pith-number/XXFUX44HA2HYO4C37RVEFYGCWC/events.json","paper":"https://pith.science/paper/XXFUX44H"},"agent_actions":{"view_html":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC","download_json":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC.json","view_paper":"https://pith.science/paper/XXFUX44H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17433&json=true","fetch_graph":"https://pith.science/api/pith-number/XXFUX44HA2HYO4C37RVEFYGCWC/graph.json","fetch_events":"https://pith.science/api/pith-number/XXFUX44HA2HYO4C37RVEFYGCWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC/action/storage_attestation","attest_author":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC/action/author_attestation","sign_citation":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC/action/citation_signature","submit_replication":"https://pith.science/pith/XXFUX44HA2HYO4C37RVEFYGCWC/action/replication_record"}},"created_at":"2026-07-05T09:11:53.854606+00:00","updated_at":"2026-07-05T09:11:53.854606+00:00"}