{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:635DZ35L5SPNEW4JJSYEZNA6SQ","short_pith_number":"pith:635DZ35L","schema_version":"1.0","canonical_sha256":"f6fa3cefabec9ed25b894cb04cb41e9403278839c9388bec98c3cdd71ef319e6","source":{"kind":"arxiv","id":"2505.24306","version":2},"attestation_state":"computed","paper":{"title":"GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chang Xu, Kechen Li, Quanwei Sun, Tianbo Ji, Ximing Wen, Xizhe Zhang, Yaotian Tao, Zifei Gong","submitted_at":"2025-05-30T07:40:59Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have demonstrated their potential in planning and reasoning tasks, offering a flexible alternative to classical pathfinding algorithms. However, most existing studies focus on LLMs' independent reasoning capabilities and overlook the potential synergy between LLMs and traditional algorithms. To fill this gap, we propose a comprehensive evaluation benchmark GridRoute to assess how LLMs can take advantage of traditional algorithms. We also propose a novel hybrid prompting technique called Algorithm of Thought (AoT), which introduces traditional"},"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":"2505.24306","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T07:40:59Z","cross_cats_sorted":[],"title_canon_sha256":"9b48bfc3cf2c3a1fc321ef8e2bc50c8373ce16bba833fe6669d10c158a6cd311","abstract_canon_sha256":"d2f04262b3d582c5aa3391167d0b73aec71f433fb1132fed95df62ef768e4471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:03.896545Z","signature_b64":"L91uvbz36W3atZvSNYIi3jcQ/naMCTQafGTeqU1GCJFPQjb5Bw0WpmnMo2V1EMDthACpEPK7gS6WVKGNPqyyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6fa3cefabec9ed25b894cb04cb41e9403278839c9388bec98c3cdd71ef319e6","last_reissued_at":"2026-07-05T11:53:03.896088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:03.896088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GridRoute: A Benchmark for LLM-Based Route Planning with Cardinal Movement in Grid Environments","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chang Xu, Kechen Li, Quanwei Sun, Tianbo Ji, Ximing Wen, Xizhe Zhang, Yaotian Tao, Zifei Gong","submitted_at":"2025-05-30T07:40:59Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have demonstrated their potential in planning and reasoning tasks, offering a flexible alternative to classical pathfinding algorithms. However, most existing studies focus on LLMs' independent reasoning capabilities and overlook the potential synergy between LLMs and traditional algorithms. To fill this gap, we propose a comprehensive evaluation benchmark GridRoute to assess how LLMs can take advantage of traditional algorithms. We also propose a novel hybrid prompting technique called Algorithm of Thought (AoT), which introduces traditional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24306","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/2505.24306/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":"2505.24306","created_at":"2026-07-05T11:53:03.896142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24306v2","created_at":"2026-07-05T11:53:03.896142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24306","created_at":"2026-07-05T11:53:03.896142+00:00"},{"alias_kind":"pith_short_12","alias_value":"635DZ35L5SPN","created_at":"2026-07-05T11:53:03.896142+00:00"},{"alias_kind":"pith_short_16","alias_value":"635DZ35L5SPNEW4J","created_at":"2026-07-05T11:53:03.896142+00:00"},{"alias_kind":"pith_short_8","alias_value":"635DZ35L","created_at":"2026-07-05T11:53:03.896142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14628","citing_title":"SmartWalkCoach: An AI Companion for End-to-End Walking Guidance, Motivation, and Reflection","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22355","citing_title":"TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09604","citing_title":"LLMs for Text-Based Exploration and Navigation Under Partial Observability","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16022","citing_title":"SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ","json":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ.json","graph_json":"https://pith.science/api/pith-number/635DZ35L5SPNEW4JJSYEZNA6SQ/graph.json","events_json":"https://pith.science/api/pith-number/635DZ35L5SPNEW4JJSYEZNA6SQ/events.json","paper":"https://pith.science/paper/635DZ35L"},"agent_actions":{"view_html":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ","download_json":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ.json","view_paper":"https://pith.science/paper/635DZ35L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24306&json=true","fetch_graph":"https://pith.science/api/pith-number/635DZ35L5SPNEW4JJSYEZNA6SQ/graph.json","fetch_events":"https://pith.science/api/pith-number/635DZ35L5SPNEW4JJSYEZNA6SQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ/action/storage_attestation","attest_author":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ/action/author_attestation","sign_citation":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ/action/citation_signature","submit_replication":"https://pith.science/pith/635DZ35L5SPNEW4JJSYEZNA6SQ/action/replication_record"}},"created_at":"2026-07-05T11:53:03.896142+00:00","updated_at":"2026-07-05T11:53:03.896142+00:00"}