{"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/smart-self-aware-agent-for-tool-overuse","title":"SMART: Self-Aware Agent for Tool Overuse Mitigation","arxiv_id":"2502.11435","date":"2025-02-17","proceeding":null,"authors":["Cheng Qian","Emre Can Acikgoz","Hongru Wang","Xiusi Chen","Avirup Sil","Dilek Hakkani-Tür","Gokhan Tur","Heng Ji"],"abstract":"Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks solvable with parametric knowledge, increasing computational overhead. Inspired by human metacognition, we introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse. To support this paradigm, we introduce SMART-ER, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary. Through supervised training, we develop SMARTAgent, a family of models that dynamically balance parametric knowledge and tool use. Evaluations show that SMARTAgent reduces tool use by 24% while improving performance by over 37%, enabling 7B-scale models to match its 70B counterpart and GPT-4o. Additionally, SMARTAgent generalizes to out-of-distribution test data like GSM8K and MINTQA, maintaining accuracy with just one-fifth the tool calls. These highlight the potential of strategic tool use to enhance reasoning, mitigate overuse, and bridge the gap between model size and performance, advancing intelligent and resource-efficient agent designs.","url_abs":"https://arxiv.org/abs/2502.11435v1","url_pdf":"https://arxiv.org/pdf/2502.11435v1.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":"smart-self-aware-agent-for-tool-overuse","repo_url":"https://github.com/qiancheng0/open-smartagent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.11435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11435"}},"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/qiancheng0/open-smartagent","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"f92d3541370c1a88","entry":"form_messages","repo":"qiancheng0/open-smartagent","repo_kind":"official","path":"evaluate/inference_eval_intention.py","file_url":"https://github.com/qiancheng0/open-smartagent/blob/HEAD/evaluate/inference_eval_intention.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f92d3541370c1a88"}},{"code_sha256_prefix":"7481a3811878bcb5","entry":"format_steps","repo":"qiancheng0/open-smartagent","repo_kind":"official","path":"inference/inference_smart.py","file_url":"https://github.com/qiancheng0/open-smartagent/blob/HEAD/inference/inference_smart.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7481a3811878bcb5"}},{"code_sha256_prefix":"24cf189579fee623","entry":"parse_steps","repo":"qiancheng0/open-smartagent","repo_kind":"official","path":"inference/inference_smart.py","file_url":"https://github.com/qiancheng0/open-smartagent/blob/HEAD/inference/inference_smart.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24cf189579fee623"}},{"code_sha256_prefix":"ad047902cc0458e3","entry":"preprocess_dataset","repo":"qiancheng0/open-smartagent","repo_kind":"official","path":"inference/inference_smart.py","file_url":"https://github.com/qiancheng0/open-smartagent/blob/HEAD/inference/inference_smart.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad047902cc0458e3"}},{"code_sha256_prefix":"c06a470ab6cf2ac9","entry":"gpt_chatcompletion","repo":"qiancheng0/open-smartagent","repo_kind":"official","path":"evaluate/inference_eval_intention.py","file_url":"https://github.com/qiancheng0/open-smartagent/blob/HEAD/evaluate/inference_eval_intention.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":"c06a470ab6cf2ac9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}