{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EJVCKAVCH6TQ4G5ONYV5RXEWIT","short_pith_number":"pith:EJVCKAVC","schema_version":"1.0","canonical_sha256":"226a2502a23fa70e1bae6e2bd8dc9644d215cffc162551cfe5ac94e7997a9c91","source":{"kind":"arxiv","id":"2303.09014","version":1},"attestation_state":"computed","paper":{"title":"ART: Automatic multi-step reasoning and tool-use for large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ART lets large language models automatically generate multi-step reasoning programs that call external tools.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhargavi Paranjape, Hannaneh Hajishirzi, Luke Zettlemoyer, Marco Tulio Ribeiro, Sameer Singh, Scott Lundberg","submitted_at":"2023-03-16T01:04:45Z","abstract_excerpt":"Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning step can rely on external tools to support computation beyond the core LLM capabilities (e.g. search/running code). Prior work on CoT prompting and tool use typically requires hand-crafting task-specific demonstrations and carefully scripted interleaving of model generations with tool use. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate re"},"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":"2303.09014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-16T01:04:45Z","cross_cats_sorted":[],"title_canon_sha256":"cad4a37e49b9b66ccfa0ac42edf9a2ea6626c8aa4df881435177bfde702d5028","abstract_canon_sha256":"fc18cfe94626e98794805db81b978304805750ed8622ad370687008a6b807ec8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.904457Z","signature_b64":"X8avq66rFKLjpQARsbbZlU06iGST1XkzkcNEFn0U540oZ7BYhAktLHT/DzV1frYEUylKYk7xmDOHqfE0dWI6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"226a2502a23fa70e1bae6e2bd8dc9644d215cffc162551cfe5ac94e7997a9c91","last_reissued_at":"2026-05-17T23:38:46.903881Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.903881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ART: Automatic multi-step reasoning and tool-use for large language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"ART lets large language models automatically generate multi-step reasoning programs that call external tools.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhargavi Paranjape, Hannaneh Hajishirzi, Luke Zettlemoyer, Marco Tulio Ribeiro, Sameer Singh, Scott Lundberg","submitted_at":"2023-03-16T01:04:45Z","abstract_excerpt":"Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning step can rely on external tools to support computation beyond the core LLM capabilities (e.g. search/running code). Prior work on CoT prompting and tool use typically requires hand-crafting task-specific demonstrations and carefully scripted interleaving of model generations with tool use. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate re"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ART achieves a substantial improvement over few-shot prompting and automatic CoT on unseen tasks in the BigBench and MMLU benchmarks, and matches performance of hand-crafted CoT prompts on a majority of these tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a fixed task library contains sufficiently diverse and high-quality demonstrations so that nearest-neighbor selection reliably supplies useful programs for entirely new, unseen tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ART lets large language models automatically generate multi-step reasoning programs that call external tools.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"28d7690fa1db8d61d0b9b4bc61bdeadc255b91c797f197c58f2bfa9570b91f50"},"source":{"id":"2303.09014","kind":"arxiv","version":1},"verdict":{"id":"ad0922ee-78ed-4279-a5e7-512d55e1bcfc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T18:58:48.398414Z","strongest_claim":"ART achieves a substantial improvement over few-shot prompting and automatic CoT on unseen tasks in the BigBench and MMLU benchmarks, and matches performance of hand-crafted CoT prompts on a majority of these tasks.","one_line_summary":"ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a fixed task library contains sufficiently diverse and high-quality demonstrations so that nearest-neighbor selection reliably supplies useful programs for entirely new, unseen tasks.","pith_extraction_headline":"ART lets large language models automatically generate multi-step reasoning programs that call external tools."},"references":{"count":267,"sample":[{"doi":"10.18653/v1/2022.acl-long.579","year":2022,"title":"Mojtaba Komeili, Kurt Shuster, and Jason Weston. 2022. https://doi.org/10.18653/v1/2022.acl-long.579 I nternet-augmented dialogue generation . In Proceedings of the 60th Annual Meeting of the Associat","work_id":"4b63a530-9990-4f21-a11b-29062ce01cc7","ref_index":15,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2021.naacl-main.168","year":2021,"title":"Are NLP Models really able to Solve Simple Math Word Problems?","work_id":"01c9a44a-5ebf-4209-a628-5f1fd19d2103","ref_index":22,"cited_arxiv_id":"2103.07191","is_internal_anchor":true},{"doi":"","year":null,"title":"Chain-of-thought prompting elicits reasoning in large language models","work_id":"f4edf7fa-4b0c-45e2-86ab-96e1d16f24bb","ref_index":33,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Finetuned Language Models Are Zero-Shot Learners","work_id":"7ed6cdaa-ed67-4db4-aceb-b7e1b0e6e7c4","ref_index":37,"cited_arxiv_id":"2109.01652","is_internal_anchor":true},{"doi":"","year":null,"title":"Chain of Thought Prompting Elicits Reasoning in Large Language Models , author=. ArXiv , year=","work_id":"75eacb63-2829-4757-8923-44fbe8ccdd56","ref_index":38,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":267,"snapshot_sha256":"da9fa28cbe2d3794c22ddf8a4347b1d0c40e7c8f03a53f49ec8b01fd2f9f98f7","internal_anchors":38},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8066222b8c40f1850eb92d5a7d0a32d7eeb36653bd62ca4232f5f123348f7d8e"},"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":"2303.09014","created_at":"2026-05-17T23:38:46.903968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09014v1","created_at":"2026-05-17T23:38:46.903968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09014","created_at":"2026-05-17T23:38:46.903968+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJVCKAVCH6TQ","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJVCKAVCH6TQ4G5O","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJVCKAVC","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":29,"sample":[{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":163,"is_internal_anchor":true},{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":217,"is_internal_anchor":true},{"citing_arxiv_id":"2506.01481","citing_title":"TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17452","citing_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2505.01441","citing_title":"Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":200,"is_internal_anchor":true},{"citing_arxiv_id":"2409.02977","citing_title":"Large Language Model-Based Agents for Software Engineering: A Survey","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"2303.17491","citing_title":"Language Models can Solve Computer Tasks","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2512.17052","citing_title":"Dynamic Tool Dependency Retrieval for Lightweight Function Calling","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2411.04468","citing_title":"Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05353","citing_title":"AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2304.08244","citing_title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2305.18323","citing_title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00827","citing_title":"Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13064","citing_title":"Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2401.10774","citing_title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2402.07927","citing_title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2211.12588","citing_title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27586","citing_title":"Trace-Level Analysis of Information Contamination in Multi-Agent Systems","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10366","citing_title":"EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05737","citing_title":"ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT","json":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT.json","graph_json":"https://pith.science/api/pith-number/EJVCKAVCH6TQ4G5ONYV5RXEWIT/graph.json","events_json":"https://pith.science/api/pith-number/EJVCKAVCH6TQ4G5ONYV5RXEWIT/events.json","paper":"https://pith.science/paper/EJVCKAVC"},"agent_actions":{"view_html":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT","download_json":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT.json","view_paper":"https://pith.science/paper/EJVCKAVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09014&json=true","fetch_graph":"https://pith.science/api/pith-number/EJVCKAVCH6TQ4G5ONYV5RXEWIT/graph.json","fetch_events":"https://pith.science/api/pith-number/EJVCKAVCH6TQ4G5ONYV5RXEWIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT/action/storage_attestation","attest_author":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT/action/author_attestation","sign_citation":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT/action/citation_signature","submit_replication":"https://pith.science/pith/EJVCKAVCH6TQ4G5ONYV5RXEWIT/action/replication_record"}},"created_at":"2026-05-17T23:38:46.903968+00:00","updated_at":"2026-05-17T23:38:46.903968+00:00"}