{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/toolllm-facilitating-large-language-models-to","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","arxiv_id":"2307.16789","date":"2023-07-31","proceeding":null,"authors":["Yujia Qin","Shihao Liang","Yining Ye","Kunlun Zhu","Lan Yan","Yaxi Lu","Yankai Lin","Xin Cong","Xiangru Tang","Bill Qian","Sihan Zhao","Lauren Hong","Runchu Tian","Ruobing Xie","Jie zhou","Mark Gerstein","Dahai Li","Zhiyuan Liu","Maosong Sun"],"abstract":"Despite the advancements of open-source large language models (LLMs), e.g., LLaMA, they remain significantly limited in tool-use capabilities, i.e., using external tools (APIs) to fulfill human instructions. The reason is that current instruction tuning largely focuses on basic language tasks but ignores the tool-use domain. This is in contrast to the excellent tool-use capabilities of state-of-the-art (SOTA) closed-source LLMs, e.g., ChatGPT. To bridge this gap, we introduce ToolLLM, a general tool-use framework encompassing data construction, model training, and evaluation. We first present ToolBench, an instruction-tuning dataset for tool use, which is constructed automatically using ChatGPT. Specifically, the construction can be divided into three stages: (i) API collection: we collect 16,464 real-world RESTful APIs spanning 49 categories from RapidAPI Hub; (ii) instruction generation: we prompt ChatGPT to generate diverse instructions involving these APIs, covering both single-tool and multi-tool scenarios; (iii) solution path annotation: we use ChatGPT to search for a valid solution path (chain of API calls) for each instruction. To enhance the reasoning capabilities of LLMs, we develop a novel depth-first search-based decision tree algorithm. It enables LLMs to evaluate multiple reasoning traces and expand the search space. Moreover, to evaluate the tool-use capabilities of LLMs, we develop an automatic evaluator: ToolEval. Based on ToolBench, we fine-tune LLaMA to obtain an LLM ToolLLaMA, and equip it with a neural API retriever to recommend appropriate APIs for each instruction. Experiments show that ToolLLaMA demonstrates a remarkable ability to execute complex instructions and generalize to unseen APIs, and exhibits comparable performance to ChatGPT. Our ToolLLaMA also demonstrates strong zero-shot generalization ability in an out-of-distribution tool-use dataset: APIBench.","url_abs":"https://arxiv.org/abs/2307.16789v2","url_pdf":"https://arxiv.org/pdf/2307.16789v2.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":"toolllm-facilitating-large-language-models-to","repo_url":"https://github.com/openbmb/toolbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"toolllm-facilitating-large-language-models-to","repo_url":"https://github.com/eachsheep/shortcutsbench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"trajectory-planning","task_name":"Trajectory Planning"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[{"slug":"toolbench","name":"ToolBench","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/trajectory-planning-on-toolbench","task":"Trajectory Planning","dataset":"ToolBench","model":"GPT4- DFSDT","rank_in_archive_order":3,"of":3,"metrics":{"Win rate":"70.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.16789","atlas_url":"https://app.syntology.ai/?focus=2307.16789","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2307.16789"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2307.16789\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2307.16789"},"call":"get_concepts_for_paper(arxiv_id=\"2307.16789\")"}],"by_repo":[{"repo":"openbmb/toolbench","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.07714"],"harvested_for_calls":[{"arxiv_id":"2403.07714","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.07714"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.07714\")"}]},{"repo":"eachsheep/shortcutsbench","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2407.00132"],"harvested_for_calls":[{"arxiv_id":"2407.00132","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2407.00132"},"call":"get_harvested_code_for_paper(arxiv_id=\"2407.00132\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"cec662d351473e4092da850a9ed5af707bc7825440470a29c770944adaa2859e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}