{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DNU2AE2SZQTBHVNXTZCLCQHK2E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0d8782eb89c1a9d7c702d20e16a11bfd1bc46d72f53065b09341e87b4526d54a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:39:01Z","title_canon_sha256":"b6d2a7268423d70738dd2d7458eaeaf6a9bdb639657a065b9b3c9d5e747df7aa"},"schema_version":"1.0","source":{"id":"2408.06318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06318","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06318v1","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06318","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_12","alias_value":"DNU2AE2SZQTB","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_16","alias_value":"DNU2AE2SZQTBHVNX","created_at":"2026-07-05T08:54:39Z"},{"alias_kind":"pith_short_8","alias_value":"DNU2AE2S","created_at":"2026-07-05T08:54:39Z"}],"graph_snapshots":[{"event_id":"sha256:3c3b44b975def0dff70c9fa8ab88565ea2d375d3995e638cd573ad6d8e466dd7","target":"graph","created_at":"2026-07-05T08:54:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.06318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ali Pesaranghader, Dong Hoon Yi, Tanmana Sadhu, Yanan Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:39:01Z","title":"Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06318","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1f4062e561d04186fcacdfb7ed9c728f96411c3c36d702457433a8719d9b64fd","target":"record","created_at":"2026-07-05T08:54:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0d8782eb89c1a9d7c702d20e16a11bfd1bc46d72f53065b09341e87b4526d54a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:39:01Z","title_canon_sha256":"b6d2a7268423d70738dd2d7458eaeaf6a9bdb639657a065b9b3c9d5e747df7aa"},"schema_version":"1.0","source":{"id":"2408.06318","kind":"arxiv","version":1}},"canonical_sha256":"1b69a01352cc2613d5b79e44b140ead115e777562a6b44699a39c56c7b03ccf0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b69a01352cc2613d5b79e44b140ead115e777562a6b44699a39c56c7b03ccf0","first_computed_at":"2026-07-05T08:54:39.016114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:39.016114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9upz3rFGGf1/Q5o4AeLl2l5OozchmkXb0w8l7Uk3EERSZPtmb9us7LllkBVUu/nJd1V52VRBL+h/6RbVljfiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:39.016579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f4062e561d04186fcacdfb7ed9c728f96411c3c36d702457433a8719d9b64fd","sha256:3c3b44b975def0dff70c9fa8ab88565ea2d375d3995e638cd573ad6d8e466dd7"],"state_sha256":"cfd82bac1cf778672c755098a55099567270acd2298db06d6a55a4fccd8c1050"}