{"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/confucius-iterative-tool-learning-from","title":"Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum","arxiv_id":"2308.14034","date":"2023-08-27","proceeding":null,"authors":["Shen Gao","Zhengliang Shi","Minghang Zhu","Bowen Fang","Xin Xin","Pengjie Ren","Zhumin Chen","Jun Ma","Zhaochun Ren"],"abstract":"Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extending the capability of LLMs. Although some works employ open-source LLMs for the tool learning task, most of them are trained in a controlled environment in which LLMs only learn to execute the human-provided tools. However, selecting proper tools from the large toolset is also a crucial ability for the tool learning model to be applied in real-world applications. Existing methods usually directly employ self-instruction methods to train the model, which ignores differences in tool complexity. In this paper, we propose the Confucius, a novel tool learning framework to train LLM to use complicated tools in real-world scenarios, which contains two main phases: (1) We first propose a multi-stage learning method to teach the LLM to use various tools from an easy-to-difficult curriculum; (2) thenceforth, we propose the Iterative Self-instruct from Introspective Feedback (ISIF) to dynamically construct the dataset to improve the ability to use the complicated tool. Extensive experiments conducted on both controlled and real-world settings demonstrate the superiority of our tool learning framework in the real-world application scenarios compared to both tuning-free (e.g. ChatGPT, Claude) and tuning-based baselines (e.g. GPT4Tools).","url_abs":"https://arxiv.org/abs/2308.14034v2","url_pdf":"https://arxiv.org/pdf/2308.14034v2.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":"confucius-iterative-tool-learning-from","repo_url":"https://github.com/shizhl/ctl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.14034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14034"}},"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/shizhl/ctl","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":7,"samples":[{"code_sha256_prefix":"6dbf1b2a5b901370","entry":"atoi","repo":"shizhl/ctl","repo_kind":"official","path":"zero_to_fp.py","file_url":"https://github.com/shizhl/ctl/blob/HEAD/zero_to_fp.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6dbf1b2a5b901370"}},{"code_sha256_prefix":"3a53f3109825e747","entry":"get_model_state_file","repo":"shizhl/ctl","repo_kind":"official","path":"zero_to_fp.py","file_url":"https://github.com/shizhl/ctl/blob/HEAD/zero_to_fp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a53f3109825e747"}},{"code_sha256_prefix":"7052cf0436949e37","entry":"natural_keys","repo":"shizhl/ctl","repo_kind":"official","path":"zero_to_fp.py","file_url":"https://github.com/shizhl/ctl/blob/HEAD/zero_to_fp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7052cf0436949e37"}},{"code_sha256_prefix":"b8baac404d72acb4","entry":"prepare_inference_data","repo":"shizhl/ctl","repo_kind":"official","path":"data.py","file_url":"https://github.com/shizhl/ctl/blob/HEAD/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8baac404d72acb4"}},{"code_sha256_prefix":"c3571b493dbf1a3d","entry":"preprocess","repo":"shizhl/ctl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/shizhl/ctl/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3571b493dbf1a3d"}},{"code_sha256_prefix":"66405e71355d1fec","entry":"load_pl_ds_checkpoint","repo":"shizhl/ctl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/shizhl/ctl/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66405e71355d1fec"}},{"code_sha256_prefix":"b18b5e8aa8f6dc7b","entry":"make_model_tokenizer","repo":"shizhl/ctl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/shizhl/ctl/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b18b5e8aa8f6dc7b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}