{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/art-automatic-multi-step-reasoning-and-tool","title":"ART: Automatic multi-step reasoning and tool-use for large language models","arxiv_id":"2303.09014","date":"2023-03-16","proceeding":null,"authors":["Bhargavi Paranjape","Scott Lundberg","Sameer Singh","Hannaneh Hajishirzi","Luke Zettlemoyer","Marco Tulio Ribeiro"],"abstract":"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 reasoning steps as a program. Given a new task to solve, ART selects demonstrations of multi-step reasoning and tool use from a task library. At test time, ART seamlessly pauses generation whenever external tools are called, and integrates their output before resuming generation. 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. ART is also extensible, and makes it easy for humans to improve performance by correcting errors in task-specific programs or incorporating new tools, which we demonstrate by drastically improving performance on select tasks with minimal human intervention.","url_abs":"https://arxiv.org/abs/2303.09014v1","url_pdf":"https://arxiv.org/pdf/2303.09014v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"art-automatic-multi-step-reasoning-and-tool","repo_url":"https://github.com/guidance-ai/guidance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"art-automatic-multi-step-reasoning-and-tool","repo_url":"https://github.com/microsoft/guidance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"mmlu","task_name":"MMLU"}],"methods":[{"method_slug":"cot-prompting","method_name":"CoT Prompting"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.09014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09014"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/guidance","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guidance-ai/guidance","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"033556b7164ece93","entry":"bytes_from","repo":"guidance-ai/guidance","repo_kind":"listed","path":"guidance/_utils.py","file_url":"https://github.com/guidance-ai/guidance/blob/HEAD/guidance/_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"033556b7164ece93"}},{"code_sha256_prefix":"c46a047369ef391b","entry":"load_template_class","repo":"guidance-ai/guidance","repo_kind":"listed","path":"guidance/chat.py","file_url":"https://github.com/guidance-ai/guidance/blob/HEAD/guidance/chat.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c46a047369ef391b"}},{"code_sha256_prefix":"a57daecf6c38000d","entry":"make_weak_bound_method","repo":"guidance-ai/guidance","repo_kind":"listed","path":"guidance/_utils.py","file_url":"https://github.com/guidance-ai/guidance/blob/HEAD/guidance/_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a57daecf6c38000d"}},{"code_sha256_prefix":"7229c1c8ee90348f","entry":"strip_multiline_string_indents","repo":"guidance-ai/guidance","repo_kind":"listed","path":"guidance/_utils.py","file_url":"https://github.com/guidance-ai/guidance/blob/HEAD/guidance/_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7229c1c8ee90348f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}