{"work":{"id":"e900f660-9178-4fda-ad54-a788e23aa0d8","openalex_id":null,"doi":null,"arxiv_id":"2306.05301","raw_key":null,"title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","authors":null,"authors_text":"Qiaoyu Tang, Ziliang Deng, Hongyu Lin, Xianpei Han, Qiao Liang, Boxi Cao","year":2023,"venue":"cs.CL","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.","external_url":"https://arxiv.org/abs/2306.05301","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-23T21:13:27.998328+00:00","pith_arxiv_id":"2306.05301","created_at":"2026-05-10T11:25:20.364105+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","render_title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases"},"hub":{"state":{"work_id":"e900f660-9178-4fda-ad54-a788e23aa0d8","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":32,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2023-04-14T14:05:32+00:00","last_pith_cited_at":"2026-05-21T14:45:02+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":"2026-06-09T16:05:20.532433+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}