{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DNU2AE2SZQTBHVNXTZCLCQHK2E","short_pith_number":"pith:DNU2AE2S","schema_version":"1.0","canonical_sha256":"1b69a01352cc2613d5b79e44b140ead115e777562a6b44699a39c56c7b03ccf0","source":{"kind":"arxiv","id":"2408.06318","version":1},"attestation_state":"computed","paper":{"title":"Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ali Pesaranghader, Dong Hoon Yi, Tanmana Sadhu, Yanan Chen","submitted_at":"2024-08-12T17:39:01Z","abstract_excerpt":"Large language models (LLMs) have brought autonomous agents closer to artificial general intelligence (AGI) due to their promising generalization and emergent capabilities. There is, however, a lack of studies on how LLM-based agents behave, why they could potentially fail, and how to improve them, particularly in demanding real-world planning tasks. In this paper, as an effort to fill the gap, we present our study using a realistic benchmark, TravelPlanner, where an agent must meet multiple constraints to generate accurate plans. We leverage this benchmark to address four key research questio"},"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":"2408.06318","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:39:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b6d2a7268423d70738dd2d7458eaeaf6a9bdb639657a065b9b3c9d5e747df7aa","abstract_canon_sha256":"0d8782eb89c1a9d7c702d20e16a11bfd1bc46d72f53065b09341e87b4526d54a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:39.016579Z","signature_b64":"9upz3rFGGf1/Q5o4AeLl2l5OozchmkXb0w8l7Uk3EERSZPtmb9us7LllkBVUu/nJd1V52VRBL+h/6RbVljfiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b69a01352cc2613d5b79e44b140ead115e777562a6b44699a39c56c7b03ccf0","last_reissued_at":"2026-07-05T08:54:39.016114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:39.016114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ali Pesaranghader, Dong Hoon Yi, Tanmana Sadhu, Yanan Chen","submitted_at":"2024-08-12T17:39:01Z","abstract_excerpt":"Large language models (LLMs) have brought autonomous agents closer to artificial general intelligence (AGI) due to their promising generalization and emergent capabilities. There is, however, a lack of studies on how LLM-based agents behave, why they could potentially fail, and how to improve them, particularly in demanding real-world planning tasks. In this paper, as an effort to fill the gap, we present our study using a realistic benchmark, TravelPlanner, where an agent must meet multiple constraints to generate accurate plans. We leverage this benchmark to address four key research questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06318","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/2408.06318/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":"2408.06318","created_at":"2026-07-05T08:54:39.016171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06318v1","created_at":"2026-07-05T08:54:39.016171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06318","created_at":"2026-07-05T08:54:39.016171+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNU2AE2SZQTB","created_at":"2026-07-05T08:54:39.016171+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNU2AE2SZQTBHVNX","created_at":"2026-07-05T08:54:39.016171+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNU2AE2S","created_at":"2026-07-05T08:54:39.016171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":199,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23883","citing_title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2603.00977","citing_title":"HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21354","citing_title":"Decoupled Travel Planning with Behavior Forest","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E","json":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E.json","graph_json":"https://pith.science/api/pith-number/DNU2AE2SZQTBHVNXTZCLCQHK2E/graph.json","events_json":"https://pith.science/api/pith-number/DNU2AE2SZQTBHVNXTZCLCQHK2E/events.json","paper":"https://pith.science/paper/DNU2AE2S"},"agent_actions":{"view_html":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E","download_json":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E.json","view_paper":"https://pith.science/paper/DNU2AE2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06318&json=true","fetch_graph":"https://pith.science/api/pith-number/DNU2AE2SZQTBHVNXTZCLCQHK2E/graph.json","fetch_events":"https://pith.science/api/pith-number/DNU2AE2SZQTBHVNXTZCLCQHK2E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E/action/storage_attestation","attest_author":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E/action/author_attestation","sign_citation":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E/action/citation_signature","submit_replication":"https://pith.science/pith/DNU2AE2SZQTBHVNXTZCLCQHK2E/action/replication_record"}},"created_at":"2026-07-05T08:54:39.016171+00:00","updated_at":"2026-07-05T08:54:39.016171+00:00"}