{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZNONLZV2W4H3RYQXWM6EPPPO2I","short_pith_number":"pith:ZNONLZV2","schema_version":"1.0","canonical_sha256":"cb5cd5e6bab70fb8e217b33c47bdeed22591fe466ca5c63466e6b7bfdccb5f2c","source":{"kind":"arxiv","id":"2509.21842","version":2},"attestation_state":"computed","paper":{"title":"DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hao Liu, Jun Fang, Jun Wang, Kai Chen, Kan Zheng, Naiqiang Tan, Rui Liu, Wei Li, Yansong Ning","submitted_at":"2025-09-26T04:03:52Z","abstract_excerpt":"Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generation, ensuring an enjoyable user experience. Despite its benefits, existing studies rely on hand-craft prompt and fixed agent workflow, hindering more flexible and autonomous TP agents. This paper proposes DeepTravel, an end-to-end agentic reinforcement learning framework for building an autonomous travel planning agent, capable of autonomously planning, executing tools, and reflecting on tool responses to explore, verify, and refine intermediate act"},"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":"2509.21842","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-26T04:03:52Z","cross_cats_sorted":[],"title_canon_sha256":"c26627e911e8ec2ae997757809c757e814688c9e9de8c859f5ee0320cc2b01ab","abstract_canon_sha256":"69615fd0850c236786b4853ff7fe3ef65054495ee5a4dcc1ab97809335f7d7a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:20:47.837108Z","signature_b64":"SFjOgxFvwebSi87d5b06e7MMu5KkNcB8swMTghR5JoYt7CmgFdAMbKgrRA+5miVAA42Ohy68eazhayienilJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb5cd5e6bab70fb8e217b33c47bdeed22591fe466ca5c63466e6b7bfdccb5f2c","last_reissued_at":"2026-07-15T01:20:47.836187Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:20:47.836187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hao Liu, Jun Fang, Jun Wang, Kai Chen, Kan Zheng, Naiqiang Tan, Rui Liu, Wei Li, Yansong Ning","submitted_at":"2025-09-26T04:03:52Z","abstract_excerpt":"Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools/resources for travel itinerary generation, ensuring an enjoyable user experience. Despite its benefits, existing studies rely on hand-craft prompt and fixed agent workflow, hindering more flexible and autonomous TP agents. This paper proposes DeepTravel, an end-to-end agentic reinforcement learning framework for building an autonomous travel planning agent, capable of autonomously planning, executing tools, and reflecting on tool responses to explore, verify, and refine intermediate act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.21842","kind":"arxiv","version":2},"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/2509.21842/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":"2509.21842","created_at":"2026-07-15T01:20:47.836641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.21842v2","created_at":"2026-07-15T01:20:47.836641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.21842","created_at":"2026-07-15T01:20:47.836641+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNONLZV2W4H3","created_at":"2026-07-15T01:20:47.836641+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNONLZV2W4H3RYQX","created_at":"2026-07-15T01:20:47.836641+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNONLZV2","created_at":"2026-07-15T01:20:47.836641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.25200","citing_title":"GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2512.22673","citing_title":"Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03308","citing_title":"Revisiting the Travel Planning Capabilities of Large Language Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08178","citing_title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08178","citing_title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I","json":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I.json","graph_json":"https://pith.science/api/pith-number/ZNONLZV2W4H3RYQXWM6EPPPO2I/graph.json","events_json":"https://pith.science/api/pith-number/ZNONLZV2W4H3RYQXWM6EPPPO2I/events.json","paper":"https://pith.science/paper/ZNONLZV2"},"agent_actions":{"view_html":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I","download_json":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I.json","view_paper":"https://pith.science/paper/ZNONLZV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.21842&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNONLZV2W4H3RYQXWM6EPPPO2I/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNONLZV2W4H3RYQXWM6EPPPO2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I/action/storage_attestation","attest_author":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I/action/author_attestation","sign_citation":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I/action/citation_signature","submit_replication":"https://pith.science/pith/ZNONLZV2W4H3RYQXWM6EPPPO2I/action/replication_record"}},"created_at":"2026-07-15T01:20:47.836641+00:00","updated_at":"2026-07-15T01:20:47.836641+00:00"}