{"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/smartcal-an-approach-to-self-aware-tool-use","title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","arxiv_id":"2412.12151","date":"2024-12-11","proceeding":null,"authors":["Yuanhao Shen","Xiaodan Zhu","Lei Chen"],"abstract":"The tool-use ability of Large Language Models (LLMs) has a profound impact on a wide range of industrial applications. However, LLMs' self-control and calibration capability in appropriately using tools remains understudied. The problem is consequential as it raises potential risks of degraded performance and poses a threat to the trustworthiness of the models. In this paper, we conduct a study on a family of state-of-the-art LLMs on three datasets with two mainstream tool-use frameworks. Our study reveals the tool-abuse behavior of LLMs, a tendency for models to misuse tools with overconfidence. We also find that this is a common issue regardless of model capability. Accordingly, we propose a novel approach, \\textit{SMARTCAL}, to mitigate the observed issues, and our results show an average of 8.6 percent increase in the QA performance and a 21.6 percent decrease in Expected Calibration Error (ECE) compared to baseline models.","url_abs":"https://arxiv.org/abs/2412.12151v1","url_pdf":"https://arxiv.org/pdf/2412.12151v1.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":"smartcal-an-approach-to-self-aware-tool-use","repo_url":"https://github.com/henrysyh2000/smartcal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.12151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12151"}},"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/henrysyh2000/smartcal","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Henrysyh2000/SMARTCAL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"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":"da6cb4abeef41a45","entry":"calculate_average","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/create_sample.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/create_sample.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da6cb4abeef41a45"}},{"code_sha256_prefix":"219b8d0fcf748400","entry":"check_answer","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/metric.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"219b8d0fcf748400"}},{"code_sha256_prefix":"9de0005083fe612d","entry":"check_answer_new","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/metric.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/metric.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9de0005083fe612d"}},{"code_sha256_prefix":"5bcaf0a56a3a5f6a","entry":"cleanhtml","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/sequential_interpreter.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/sequential_interpreter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5bcaf0a56a3a5f6a"}},{"code_sha256_prefix":"a442b0bd917515d1","entry":"exact_match","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/art_uw.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/art_uw.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a442b0bd917515d1"}},{"code_sha256_prefix":"efe7932c4c2edafd","entry":"finqa_equal","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/pot_tools.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/pot_tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efe7932c4c2edafd"}},{"code_sha256_prefix":"189de55b9f8a0629","entry":"format_answers","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/create_sample.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/create_sample.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"189de55b9f8a0629"}},{"code_sha256_prefix":"5032f10ada38d45d","entry":"get_precision","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/pot_tools.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/pot_tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5032f10ada38d45d"}},{"code_sha256_prefix":"28c9120c7dd08f39","entry":"get_subset","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/utils.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"28c9120c7dd08f39"}},{"code_sha256_prefix":"cbe8ae02fd4f5c06","entry":"load_mintaka","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/create_sample.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/create_sample.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cbe8ae02fd4f5c06"}},{"code_sha256_prefix":"ca20cb9ad005aa47","entry":"random_tasks","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/prompt_library.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/prompt_library.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca20cb9ad005aa47"}},{"code_sha256_prefix":"4d8b1a7898526649","entry":"search","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/sequential_interpreter.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/sequential_interpreter.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d8b1a7898526649"}},{"code_sha256_prefix":"674b9427b4e0d492","entry":"simplify_ans","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/pot_tools.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/pot_tools.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"674b9427b4e0d492"}},{"code_sha256_prefix":"ed0f66014daff74a","entry":"token_match","repo":"Henrysyh2000/SMARTCAL","repo_kind":"official","path":"ART_SM_CAL/art_uw.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/art_uw.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed0f66014daff74a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}