{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7DAJ5VMYBAGAUVYJSG4AL2K7BG","short_pith_number":"pith:7DAJ5VMY","schema_version":"1.0","canonical_sha256":"f8c09ed598080c0a570991b805e95f0990be0883e5b3573bd69666127dbbd0f6","source":{"kind":"arxiv","id":"2305.10276","version":7},"attestation_state":"computed","paper":{"title":"Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanxu Hu, Hongyuan Lu, Huajian Zhang, Wai Lam, Yue Zhang, Yun-Ze Song","submitted_at":"2023-05-17T15:07:50Z","abstract_excerpt":"In this paper, we take the initiative to investigate the performance of LLMs on complex planning tasks that require LLMs to understand a virtual spatial environment simulated via natural language and act correspondingly in text. We propose a benchmark named Natural Language Planning and Action (Natala) composed of a set of novel tasks: Brick World, NLVR-based Manipulations, and Natural Language Navigation. We found that current popular LLMs such as ChatGPT still lack abilities in complex planning. This arises a question -- do the LLMs have a good understanding of the environments described in "},"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":"2305.10276","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:07:50Z","cross_cats_sorted":[],"title_canon_sha256":"27e2c2d6108ac3b940995e63b0e56fbd8497f4fe76011857941c8f5a95bbec7e","abstract_canon_sha256":"cfb3549a98fa844e552bfbeb3ab91b918c9d00a270c994a4f8c07293feeacc7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:41.733060Z","signature_b64":"N1egkPamVN92s/+zudzRntbrebS8IHxmJx9z6TixT7ay/MwTf7niOrtfzNow7mFZWV53TScHxSheUxXybhCrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c09ed598080c0a570991b805e95f0990be0883e5b3573bd69666127dbbd0f6","last_reissued_at":"2026-07-05T08:51:41.732577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:41.732577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanxu Hu, Hongyuan Lu, Huajian Zhang, Wai Lam, Yue Zhang, Yun-Ze Song","submitted_at":"2023-05-17T15:07:50Z","abstract_excerpt":"In this paper, we take the initiative to investigate the performance of LLMs on complex planning tasks that require LLMs to understand a virtual spatial environment simulated via natural language and act correspondingly in text. We propose a benchmark named Natural Language Planning and Action (Natala) composed of a set of novel tasks: Brick World, NLVR-based Manipulations, and Natural Language Navigation. We found that current popular LLMs such as ChatGPT still lack abilities in complex planning. This arises a question -- do the LLMs have a good understanding of the environments described in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10276","kind":"arxiv","version":7},"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/2305.10276/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":"2305.10276","created_at":"2026-07-05T08:51:41.732638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10276v7","created_at":"2026-07-05T08:51:41.732638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10276","created_at":"2026-07-05T08:51:41.732638+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DAJ5VMYBAGA","created_at":"2026-07-05T08:51:41.732638+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DAJ5VMYBAGAUVYJ","created_at":"2026-07-05T08:51:41.732638+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DAJ5VMY","created_at":"2026-07-05T08:51:41.732638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12358","citing_title":"From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehicles","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02812","citing_title":"Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02812","citing_title":"Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG","json":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG.json","graph_json":"https://pith.science/api/pith-number/7DAJ5VMYBAGAUVYJSG4AL2K7BG/graph.json","events_json":"https://pith.science/api/pith-number/7DAJ5VMYBAGAUVYJSG4AL2K7BG/events.json","paper":"https://pith.science/paper/7DAJ5VMY"},"agent_actions":{"view_html":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG","download_json":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG.json","view_paper":"https://pith.science/paper/7DAJ5VMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10276&json=true","fetch_graph":"https://pith.science/api/pith-number/7DAJ5VMYBAGAUVYJSG4AL2K7BG/graph.json","fetch_events":"https://pith.science/api/pith-number/7DAJ5VMYBAGAUVYJSG4AL2K7BG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG/action/storage_attestation","attest_author":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG/action/author_attestation","sign_citation":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG/action/citation_signature","submit_replication":"https://pith.science/pith/7DAJ5VMYBAGAUVYJSG4AL2K7BG/action/replication_record"}},"created_at":"2026-07-05T08:51:41.732638+00:00","updated_at":"2026-07-05T08:51:41.732638+00:00"}