{"work":{"id":"0bffef46-48af-4851-abce-a3d6792d044b","openalex_id":"https://openalex.org/W4327810433","doi":"10.48550/arxiv.2303.09014","arxiv_id":"2303.09014","raw_key":null,"title":"ART: Automatic multi-step reasoning and tool-use for large language models","authors":null,"authors_text":"Bhargavi Paranjape, Scott Lundberg, Sameer Singh, Hannaneh Hajishirzi, Luke Zettlemoyer, Marco Tulio Ribeiro","year":2023,"venue":"cs.CL","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.","external_url":"https://arxiv.org/abs/2303.09014","cited_by_count":50,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2303.09014","created_at":"2026-05-09T06:05:33.938160+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"ART: Automatic multi-step reasoning and tool-use for large language models","render_title":"ART: Automatic multi-step reasoning and tool-use for large language models"},"hub":{"state":{"work_id":"0bffef46-48af-4851-abce-a3d6792d044b","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":37,"external_cited_by_count":50,"distinct_field_count":9,"first_pith_cited_at":"2022-11-22T21:06:00+00:00","last_pith_cited_at":"2026-07-09T17:59:32+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-21T16:09:45.722881+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":7}],"polarity_counts":[{"context_polarity":"background","n":6},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}