{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5QCAUIUFOMSNTLTDFDYRTMYVR4","short_pith_number":"pith:5QCAUIUF","schema_version":"1.0","canonical_sha256":"ec040a22857324d9ae6328f119b3158f025362a9aca97754eabb85d5de802efd","source":{"kind":"arxiv","id":"2403.12881","version":1},"attestation_state":"computed","paper":{"title":"Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Feng Zhao, Jiangning Liu, Kai Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Zehui Chen","submitted_at":"2024-03-19T16:26:10Z","abstract_excerpt":"Open-sourced Large Language Models (LLMs) have achieved great success in various NLP tasks, however, they are still far inferior to API-based models when acting as agents. How to integrate agent ability into general LLMs becomes a crucial and urgent problem. This paper first delivers three key observations: (1) the current agent training corpus is entangled with both formats following and agent reasoning, which significantly shifts from the distribution of its pre-training data; (2) LLMs exhibit different learning speeds on the capabilities required by agent tasks; and (3) current approaches h"},"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":"2403.12881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-19T16:26:10Z","cross_cats_sorted":[],"title_canon_sha256":"632b3afbaddb3de32b54519be10519e6a1a8ba1421fc621399b1d984195bd524","abstract_canon_sha256":"8866d0a714c340f3330dcb2060944226d449c2a34c6ee85994370aea4a383c6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:09.017725Z","signature_b64":"mTdnx6QBJgAssChoNQUrDl3pwLQ231rf8t/72atwK+QvZIbxU/VNffDSEAleSJ5zfDjVw3QPvahtv3lEQcNDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec040a22857324d9ae6328f119b3158f025362a9aca97754eabb85d5de802efd","last_reissued_at":"2026-07-05T07:58:09.017208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:09.017208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Feng Zhao, Jiangning Liu, Kai Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Zehui Chen","submitted_at":"2024-03-19T16:26:10Z","abstract_excerpt":"Open-sourced Large Language Models (LLMs) have achieved great success in various NLP tasks, however, they are still far inferior to API-based models when acting as agents. How to integrate agent ability into general LLMs becomes a crucial and urgent problem. This paper first delivers three key observations: (1) the current agent training corpus is entangled with both formats following and agent reasoning, which significantly shifts from the distribution of its pre-training data; (2) LLMs exhibit different learning speeds on the capabilities required by agent tasks; and (3) current approaches h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12881","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/2403.12881/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":"2403.12881","created_at":"2026-07-05T07:58:09.017270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12881v1","created_at":"2026-07-05T07:58:09.017270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12881","created_at":"2026-07-05T07:58:09.017270+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QCAUIUFOMSN","created_at":"2026-07-05T07:58:09.017270+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QCAUIUFOMSNTLTD","created_at":"2026-07-05T07:58:09.017270+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QCAUIUF","created_at":"2026-07-05T07:58:09.017270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21740","citing_title":"Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18051","citing_title":"Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03610","citing_title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4","json":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4.json","graph_json":"https://pith.science/api/pith-number/5QCAUIUFOMSNTLTDFDYRTMYVR4/graph.json","events_json":"https://pith.science/api/pith-number/5QCAUIUFOMSNTLTDFDYRTMYVR4/events.json","paper":"https://pith.science/paper/5QCAUIUF"},"agent_actions":{"view_html":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4","download_json":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4.json","view_paper":"https://pith.science/paper/5QCAUIUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12881&json=true","fetch_graph":"https://pith.science/api/pith-number/5QCAUIUFOMSNTLTDFDYRTMYVR4/graph.json","fetch_events":"https://pith.science/api/pith-number/5QCAUIUFOMSNTLTDFDYRTMYVR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4/action/storage_attestation","attest_author":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4/action/author_attestation","sign_citation":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4/action/citation_signature","submit_replication":"https://pith.science/pith/5QCAUIUFOMSNTLTDFDYRTMYVR4/action/replication_record"}},"created_at":"2026-07-05T07:58:09.017270+00:00","updated_at":"2026-07-05T07:58:09.017270+00:00"}