{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FQMCDKHNVWX7RW6KQIJFTMP55X","short_pith_number":"pith:FQMCDKHN","schema_version":"1.0","canonical_sha256":"2c1821a8edadaff8dbca821259b1fdedc7d205881b6610029e1f9bfde20428ce","source":{"kind":"arxiv","id":"2305.04091","version":3},"attestation_state":"computed","paper":{"title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ee-Peng Lim, Lei Wang, Roy Ka-Wei Lee, Wanyu Xu, Yihuai Lan, Yunshi Lan, Zhiqiang Hu","submitted_at":"2023-05-06T16:34:37Z","abstract_excerpt":"Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zero-shot-CoT concatenates the target problem statement with \"Let's think step by step\" as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation erro"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2305.04091","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-06T16:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"f56516d1ca947cb363110d8bea974c14791c50e9325777e0a715a28c362e970d","abstract_canon_sha256":"f065ef4bf5e68e80903b1ad1da282d69025925c2b3235bae6ac3930ef1d10a4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.467490Z","signature_b64":"0Ezq/Y76dBJPKZ1ZKEfnTACgSNgCoOTBXGKfTiQ7e7KGWekfMamw2n4DHaTTRmrmXZK4uFqalj7dAGYFUCX7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c1821a8edadaff8dbca821259b1fdedc7d205881b6610029e1f9bfde20428ce","last_reissued_at":"2026-05-17T23:38:48.467034Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.467034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ee-Peng Lim, Lei Wang, Roy Ka-Wei Lee, Wanyu Xu, Yihuai Lan, Yunshi Lan, Zhiqiang Hu","submitted_at":"2023-05-06T16:34:37Z","abstract_excerpt":"Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zero-shot-CoT concatenates the target problem statement with \"Let's think step by step\" as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation erro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed gains arise specifically from the plan-then-solve structure rather than from increased prompt length, additional instructions, or other uncontrolled prompt-engineering factors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Plan-and-Solve prompting improves zero-shot LLM reasoning by first creating an explicit plan then executing subtasks, outperforming simple 'think step by step' prompts across ten datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8a80f66e3f1f9c1d7f1e6df22f2072c7b98d11e28e71f28b4759a3313000f6ff"},"source":{"id":"2305.04091","kind":"arxiv","version":3},"verdict":{"id":"6b747126-1475-4eac-bbaa-f08dac9ff3c0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:40:06.485739Z","strongest_claim":"our proposed zero-shot prompting consistently outperforms Zero-shot-CoT across all datasets by a large margin, is comparable to or exceeds Zero-shot-Program-of-Thought Prompting, and has comparable performance with 8-shot CoT prompting on the math reasoning problem.","one_line_summary":"Plan-and-Solve prompting improves zero-shot LLM reasoning by first creating an explicit plan then executing subtasks, outperforming simple 'think step by step' prompts across ten datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed gains arise specifically from the plan-then-solve structure rather than from increased prompt length, additional instructions, or other uncontrolled prompt-engineering factors.","pith_extraction_headline":"Plan-and-solve prompting divides tasks into subtasks before solving them to cut missing-step errors in zero-shot chain-of-thought reasoning."},"references":{"count":25,"sample":[{"doi":"","year":2016,"title":"On the advance of making language models better reasoners.arXiv preprint arXiv:2206.02336, 2","work_id":"43823128-e3c9-4d2e-8e37-8e23c025e9d0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","work_id":"7226ffd7-2787-4b30-823a-785e230e85d1","ref_index":2,"cited_arxiv_id":"2304.11477","is_internal_anchor":true},{"doi":"","year":2080,"title":"Measuring and Narrowing the Compositionality Gap in Language Models","work_id":"79aa4add-ff4a-4871-9c74-6f473b0579c1","ref_index":3,"cited_arxiv_id":"2210.03350","is_internal_anchor":true},{"doi":"","year":2023,"title":"LaMDA: Language Models for Dialog Applications","work_id":"1b66d0a5-f6ae-4332-8025-c662dc64b238","ref_index":4,"cited_arxiv_id":"2201.08239","is_internal_anchor":true},{"doi":"","year":null,"title":"Convert A cents to dollars","work_id":"20a509f4-362a-4a5c-9eed-0ef99405d4f6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":25,"snapshot_sha256":"59d79be762bbc139cdb3f6637b76a61f5f6aa1629319a82a1837ed2383f76b4f","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f9983cbdb2bfc9b3fcf2048cba1b69baaa29a8d995e597ded4203c6dd90f6717"},"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":"2305.04091","created_at":"2026-05-17T23:38:48.467108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04091v3","created_at":"2026-05-17T23:38:48.467108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04091","created_at":"2026-05-17T23:38:48.467108+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQMCDKHNVWX7","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQMCDKHNVWX7RW6K","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQMCDKHN","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":28,"sample":[{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19099","citing_title":"DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15425","citing_title":"Runtime-Structured Task Decomposition for Agentic Coding Systems","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2506.19420","citing_title":"Commander-GPT: Dividing and Routing for Multimodal Sarcasm Detection","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":127,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":128,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04056","citing_title":"QuiLL: An LLM-Based Vulnerability Assessment Framework for the Wild","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2309.05653","citing_title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01693","citing_title":"LitMOF: An LLM Multi-Agent for Literature-Validated Metal-Organic Frameworks Database Correction and Expansion","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2603.03332","citing_title":"Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":149,"is_internal_anchor":true},{"citing_arxiv_id":"2603.06870","citing_title":"LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13391","citing_title":"RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2402.02716","citing_title":"Understanding the planning of LLM agents: A survey","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11807","citing_title":"Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27699","citing_title":"Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2307.13702","citing_title":"Measuring Faithfulness in Chain-of-Thought Reasoning","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23194","citing_title":"From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05846","citing_title":"LoopTrap: Termination Poisoning Attacks on LLM Agents","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04304","citing_title":"Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19299","citing_title":"Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06753","citing_title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X","json":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X.json","graph_json":"https://pith.science/api/pith-number/FQMCDKHNVWX7RW6KQIJFTMP55X/graph.json","events_json":"https://pith.science/api/pith-number/FQMCDKHNVWX7RW6KQIJFTMP55X/events.json","paper":"https://pith.science/paper/FQMCDKHN"},"agent_actions":{"view_html":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X","download_json":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X.json","view_paper":"https://pith.science/paper/FQMCDKHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04091&json=true","fetch_graph":"https://pith.science/api/pith-number/FQMCDKHNVWX7RW6KQIJFTMP55X/graph.json","fetch_events":"https://pith.science/api/pith-number/FQMCDKHNVWX7RW6KQIJFTMP55X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/action/storage_attestation","attest_author":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/action/author_attestation","sign_citation":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/action/citation_signature","submit_replication":"https://pith.science/pith/FQMCDKHNVWX7RW6KQIJFTMP55X/action/replication_record"}},"created_at":"2026-05-17T23:38:48.467108+00:00","updated_at":"2026-05-17T23:38:48.467108+00:00"}