{"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/toolalpaca-generalized-tool-learning-for","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","arxiv_id":"2306.05301","date":"2023-06-08","proceeding":null,"authors":["Qiaoyu Tang","Ziliang Deng","Hongyu Lin","Xianpei Han","Qiao Liang","Boxi Cao","Le Sun"],"abstract":"Enabling large language models to utilize real-world tools effectively is crucial for achieving embodied intelligence. Existing approaches to tool learning have either primarily relied on extremely large language models, such as GPT-4, to attain generalized tool-use abilities in a zero-shot manner, or utilized supervised learning to train limited scopes of tools on compact models. However, it remains uncertain whether smaller language models can achieve generalized tool-use abilities without tool-specific training. To address this question, this paper introduces ToolAlpaca, a novel framework designed to automatically generate a diverse tool-use corpus and learn generalized tool-use abilities on compact language models with minimal human intervention. Specifically, ToolAlpaca first automatically creates a highly diversified tool-use corpus by building a multi-agent simulation environment. The corpus contains 3938 tool-use instances from more than 400 real-world tool APIs spanning 50 distinct categories. Subsequently, the constructed corpus is employed to fine-tune compact language models, resulting in two models, namely ToolAlpaca-7B and ToolAlpaca-13B, respectively. Finally, we evaluate the ability of these models to utilize previously unseen tools without specific training. Experimental results demonstrate that ToolAlpaca achieves effective generalized tool-use capabilities comparable to those of extremely large language models like GPT-3.5, demonstrating that learning generalized tool-use ability is feasible for compact language models.","url_abs":"https://arxiv.org/abs/2306.05301v2","url_pdf":"https://arxiv.org/pdf/2306.05301v2.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":"toolalpaca-generalized-tool-learning-for","repo_url":"https://github.com/tangqiaoyu/ToolAlpaca","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"toolalpaca-generalized-tool-learning-for","repo_url":"https://github.com/MadeAgents/Hammer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"toolalpaca-generalized-tool-learning-for","repo_url":"https://github.com/hypasd-art/CITI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.05301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05301"}},"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/tangqiaoyu/ToolAlpaca","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hypasd-art/CITI","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MadeAgents/Hammer","reach":null}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"62b88ca460bfc8b7","entry":"async_openai_chat_completions","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62b88ca460bfc8b7"}},{"code_sha256_prefix":"c5449a50ffae9006","entry":"call_api_function","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"agent/convert_request.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/agent/convert_request.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c5449a50ffae9006"}},{"code_sha256_prefix":"471536520dab670a","entry":"clear_instructions","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"instance_generation/instruction.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/instance_generation/instruction.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"471536520dab670a"}},{"code_sha256_prefix":"b57b79f206e2e89f","entry":"convert_type","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"agent/convert_request.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/agent/convert_request.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b57b79f206e2e89f"}},{"code_sha256_prefix":"19d0dd9231c8137e","entry":"create_retry_decorator","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"19d0dd9231c8137e"}},{"code_sha256_prefix":"d0eaf42db78e498b","entry":"openai_chat_completions","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0eaf42db78e498b"}},{"code_sha256_prefix":"3ab91e1b3c64d06a","entry":"rreplace","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"build_dataset.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/build_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ab91e1b3c64d06a"}},{"code_sha256_prefix":"15a50c494e1cf139","entry":"type_check","repo":"tangqiaoyu/ToolAlpaca","repo_kind":"official","path":"agent/convert_request.py","file_url":"https://github.com/tangqiaoyu/ToolAlpaca/blob/HEAD/agent/convert_request.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15a50c494e1cf139"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}