Tool learning with large language models: a survey

Abstract

Recently, tool learning with large language models (LLMs) has emerged as a promising paradigm for augmenting the capabilities of LLMs to tackle highly complex problems. Despite growing attention and rapid advancements in this field, the existing literature remains fragmented and lacks systematic organization, posing barriers to entry for newcomers. This gap motivates us to conduct a comprehensive survey of existing works on tool learning with LLMs. In this survey, we focus on reviewing existing literature from the two primary aspects (1) why tool learning is beneficial and (2) how tool learning is implemented, enabling a comprehensive understanding of tool learning with LLMs. We first explore the “why” by reviewing both the benefits of tool integration and the inherent benefits of the tool learning paradigm from six specific aspects. In terms of “how”, we systematically review the literature according to a taxonomy of four key stages in the tool learning workflow: task planning, tool selection, tool calling, and response generation. Additionally, we provide a detailed summary of existing benchmarks and evaluation methods, categorizing them according to their relevance to different stages. Finally, we discuss current challenges and outline potential future directions, aiming to inspire both researchers and industrial developers to further explore this emerging and promising area.

Graphical abstract

Keywords

tool learning / large language models / agent

Changle Qu is currently pursuing the PhD degree at Gaoling School of Artificial Intelligence, Renmin University of China, China. His current research interests mainly include tool learning with large language models and information retrieval

Sunhao Dai is a PhD candidate at Gaoling School of Artificial Intelligence, Renmin University of China, China. His current research interests lie in recommender systems and information retrieval. He has published several papers in top-tier conferences such as KDD, SIGIR, ICDE, CIKM, and RecSys

Xiaochi Wei received PhD degree from Beijing Institute of Technology, China in 2018, under the supervision of Prof. Heyan Huang. He visited National University of Singapore, Singapore from 2015 to 2016, under the supervision of Prof. Tat-Seng Chua. He is a Senior R&D Engineer in Baidu Inc.. His research interests include question answering, multi-media information retrieval, and recommender systems. He has served as PC member in severals conferences, e.g., AAAI, IJCAI, ACL, and EMNLP

Hengyi Cai received PhD degree from Institute of Computing Technology, Chinese Academy of Sciences (Outstanding Graduate), China in 2021. He joined JD’s doctoral management trainee program in the summer of 2021. Previously, he was a research intern at Baidu’s Search Science Team in 2020, under the supervision of Dr. Dawei Yin. His research interests include dialogue system, question answering, and information retrieval. He served or is serving as PC member for top-tire conference including ACL, EMNLP, KDD, NeurIPS, and SIGIR

Shuaiqiang Wang received the BSc and PhD degrees in computer science from Shandong University, China in 2004 and 2009, respectively. He is currently a principle algorithm engineer with Baidu Inc.. Previously, he was a research scientist with JD.com. Before that, he was an Assistant Professor with the University of Manchester, UK and the University of Jyvaskyla, Finland. served as Senior PC Member of IJCAI, and PC Member of WWW, SIGIR, and WSDM in recent years. He is broadly interested in several research areas including information retrieval, recommender systems, and data mining

Dawei Yin received PhD degree from Lehigh University, USA in 2013. He is senior director of engineering with Baidu inc.. He is managing the search science team with Baidu. Previously, he was senior director, managing the recommendation engineering team with JD.com between 2016 and 2019. Prior to JD.com, he was senior research manager with Yahoo Labs, leading relevance science team and in charge of Core Search Relevance of Yahoo Search. His research interests include data mining, applied machine learning, information retrieval and recommender system. He published more than 100 research papers in premium conferences and journals, and was the recipients of WSDM 2016 Best Paper Award, KDD 2016 Best Paper Award, WSDM 2018 Best Student Paper Award

Jun Xu is a professor with the Gaoling School of Artificial Intelligence, Renmin University of China, China. His research interests focus on learning to rank and semantic matching in web search. He served or is serving as SPC for SIGIR, WWW, and AAAI, editorial board member for JASIST, and associate editor for ACM TOIS. He has won the Test of Time Award Honorable Mention in SIGIR (2019), Best Paper Award in AIRS (2010) and Best Paper Runner-up in CIKM (2017)

Ji-rong Wen is a professor of the Renmin University of China (RUC), China. He is also the dean of the School of Information and executive dean of the Gaoling School of Artificial Intelligence with RUC. His main research interests include information retrieval, data mining, and machine learning. He was a senior researcher and group manager of the Web Search and Mining Group with Microsoft Research Asia (MSRA)

References

[1] Washburn S L. Tools and human evolution. Scientific American, 1960, 203( 3): 62–75

[2] Gibson K R, Ingold T. Tools, Language, and Cognition in Human Evolution. Cambridge: Cambridge University Press, 1994

[3] Von Eckardt B. What Is Cognitive Science? The MIT Press, 1995, ISBN: 9780262720236

[4] Shumaker R W, Walkup K R, Beck B B. Animal Tool Behavior: the Use and Manufacture of Tools by Animals. Baltimore: Johns Hopkins University Press, 2011

[5] Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, , . GPT-4 technical report. 2024, arXiv preprint arXiv: 2303.08774

[6] El-Kassas W S, Salama C R, Rafea A A, Mohamed H K. Automatic text summarization: a comprehensive survey. Expert Systems with Applications, 2021, 165: 113679

[7] Zhang T, Ladhak F, Durmus E, Liang P, McKeown K, Hashimoto T B. Benchmarking large language models for news summarization. Transactions of the Association for Computational Linguistics, 2024, 12: 39–57

[8] Zhang B, Haddow B, Birch A. Prompting large language model for machine translation: a case study. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 41092–41110

[9] Feng Z, Zhang Y, Li H, Liu W, Lang J, Feng Y, Wu J, Liu Z. Improving LLM-based machine translation with systematic self-correction. 2024, arXiv preprint arXiv: 2402.16379v2

[10] Yang Z, Qi P, Zhang S, Bengio Y, Cohen W W, Salakhutdinov R, Manning C D. HotpotQA: a dataset for diverse, explainable multi-hop question answering. In: Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 2369–2380

[11] Kwiatkowski T, Palomaki J, Redfield O, Collins M, Parikh A, Alberti C, Epstein D, Polosukhin I, Devlin J, Lee K, Toutanova K, Jones L, Kelcey M, Chang M W, Dai A M, Uszkoreit J, Le Q, Petrov S. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics, 2019, 7: 452–466

[12] Mallen A, Asai A, Zhong V, Das R, Khashabi D, Hajishirzi H. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 9802–9822

[13] Vu T, Iyyer M, Wang X, Constant N, Wei J, Wei J, Tar C, Sung Y H, Zhou D, Le Q, Luong T. FreshLLMs: refreshing large language models with search engine augmentation. In: Proceedings of Findings of the Association for Computational Linguistics ACL 2024. 2024, 13697–13720

[14] Ji Z, Lee N, Frieske R, Yu T, Su D, Xu Y, Ishii E, Bang Y J, Madotto A, Fung P. Survey of hallucination in natural language generation. ACM Computing Surveys, 2023, 55( 12): 248

[15] Zhang Y, Li Y, Cui L, Cai D, Liu L, Fu T, Huang X, Zhao E, Zhang Y, Chen Y, Wang L, Luu A T, Bi W, Shi F, Shi S. Siren’s song in the AI ocean: a survey on hallucination in large language models. 2023, arXiv preprint arXiv: 2309.01219

[16] Qin Y, Hu S, Lin Y, Chen W, Ding N, , . Tool learning with foundation models. 2024, arXiv preprint arXiv: 2304.08354

[17] Schick T, Dwivedi-Yu J, Dessì R, Raileanu R, Lomeli M, Hambro E, Zettlemoyer L, Cancedda N, Scialom T. Toolformer: language models can teach themselves to use tools. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2023, 36

[18] Qin Y, Liang S, Ye Y, Zhu K, Yan L, Lu Y, Lin Y, Cong X, Tang X, Qian B, Zhao S, Hong L, Tian R, Xie R, Zhou J, Gerstein M, Li D, Liu Z, Sun M. ToolLLM: facilitating large language models to master 16000+ real-world APIs. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[19] Tang Q, Deng Z, Lin H, Han X, Liang Q, Cao B, Sun L. ToolAlpaca: generalized tool learning for language models with 3000 simulated cases. 2023, arXiv preprint arXiv: 2306.05301

[20] Wang H, Qin Y, Lin Y, Pan J Z, Wong K F. Empowering large language models: tool learning for real-world interaction. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2024, 2983–2986

[21] Yao S, Chen H, Yang J, Narasimhan K. WebShop: towards scalable real-world web interaction with grounded language agents. In: Proceedings of the 36th Conference on Neural Information Processing Systems. 2022, 20744–20757

[22] Lazaridou A, Gribovskaya E, Stokowiec W, Grigorev N. Internet-augmented language models through few-shot prompting for open-domain question answering. 2022, arXiv preprint arXiv: 2203.05115

[23] Lu Y, Yu H, Khashabi D. GEAR: augmenting language models with generalizable and efficient tool resolution. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics. 2024, 112–138

[24] Pan L, Wu X, Lu X, Luu A T, Wang W Y, Kan M Y, Nakov P. Fact-checking complex claims with program-guided reasoning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 6981–7004

[25] Wang X, Wang Z, Liu J, Chen Y, Yuan L, Peng H, Ji H. MINT: evaluating LLMs in multi-turn interaction with tools and language feedback. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[26] Parisi A, Zhao Y, Fiedel N. TALM: tool augmented language models. 2022, arXiv preprint arXiv: 2205.12255

[27] Karpas E, Abend O, Belinkov Y, Lenz B, Lieber O, Ratner N, Shoham Y, Bata H, Levine Y, Leyton-Brown K, Muhlgay D, Rozen N, Schwartz E, Shachaf G, Shalev-Shwartz S, Shashua A, Tenenholtz M. MRKL systems: a modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning. 2022, arXiv preprint arXiv: 2205.00445

[28] Nakano R, Hilton J, Balaji S, Wu J, Ouyang L, Kim C, Hesse C, Jain S, Kosaraju V, Saunders W, Jiang X, Cobbe K, Eloundou T, Krueger G, Button K, Knight M, Chess B, Schulman J. WebGPT: Browser-assisted question-answering with human feedback. 2022, arXiv preprint arXiv: 2112.09332

[29] Surís D, Menon S, Vondrick C. ViperGPT: visual inference via python execution for reasoning. In: Proceedings of 2023 IEEE/CVF International Conference on Computer Vision. 2023, 11854–11864

[30] Li M, Zhao Y, Yu B, Song F, Li H, Yu H, Li Z, Huang F, Li Y. API-Bank: a comprehensive benchmark for tool-augmented LLMs. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 3102−3116

[31] Huang Y, Shi J, Li Y, Fan C, Wu S, Zhang Q, Liu Y, Zhou P, Wan Y, Gong N Z, Sun L C. MetaTool benchmark for large language models: deciding whether to use tools and which to use. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[32] Chen Z, Du W, Zhang W, Liu K, Liu J, Zheng M, Zhuo J, Zhang S, Lin D, Chen K, Zhao F. T-Eval: evaluating the tool utilization capability of large language models step by step. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 9510−9529

[33] Xu Q, Hong F, Li B, Hu C, Chen Z, Zhang J. On the tool manipulation capability of open-source large language models. 2023, arXiv preprint arXiv: 2305.16504

[34] Gao S, Shi Z, Zhu M, Fang B, Xin X, Ren P, Chen Z, Ma J, Ren Z. Confucius: iterative tool learning from introspection feedback by easy-to-difficult curriculum. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. 2024, 18030−18038

[35] Zhao Y, Wu J, Wang X, Tang W, Wang D, De Rijke M. Let me do it for you: towards LLM empowered recommendation via tool learning. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2024, 1796−1806

[36] Zhao W X, Zhou K, Li J, Tang T, Wang X, , . A survey of large language models. 2024, arXiv preprint arXiv: 2303.18223

[37] Huang X, Liu W, Chen X, Wang X, Wang H, Lian D, Wang Y, Tang R, Chen E. Understanding the planning of LLM agents: a survey. 2024, arXiv preprint arXiv: 2402.02716

[38] Qiao S, Ou Y, Zhang N, Chen X, Yao Y, Deng S, Tan C, Huang F, Chen H. Reasoning with language model prompting: a survey. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 5368−5393

[39] Sun J, Zheng C, Xie E, Liu Z, Chu R, , . A survey of reasoning with foundation models. 2024, arXiv preprint arXiv: 2312.11562

[40] Wang L, Ma C, Feng X, Zhang Z, Yang H, Zhang J, Chen Z, Tang J, Chen X, Lin Y, Zhao W X, Wei Z, Wen J. A survey on large language model based autonomous agents. Frontiers of Computer Science, 2024, 18( 6): 186345

[41] Sumers T R, Yao S, Narasimhan K, Griffiths T L. Cognitive architectures for language agents. Transactions on Machine Learning Research, 2024, ISSN: 2835-8856

[42] Xi Z, Chen W, Guo X, He W, Ding Y, , . The rise and potential of large language model based agents: a survey. 2023, arXiv preprint arXiv: 2309.07864

[43] Gao Y, Xiong Y, Gao X, Jia K, Pan J, Bi Y, Dai Y, Sun J, Wang M, Wang H. Retrieval-augmented generation for large language models: a survey. 2024, arXiv preprint arXiv: 2312.10997

[44] Zhao P, Zhang H, Yu Q, Wang Z, Geng Y, Fu F, Yang L, Zhang W, Jiang J, Cui B. Retrieval-augmented generation for AI-generated content: a survey. 2024, arXiv preprint arXiv: 2402.19473

[45] Mialon G, Dessì R, Lomeli M, Nalmpantis C, Pasunuru R, Raileanu R, Rozière B, Schick T, Dwivedi-Yu J, Celikyilmaz A, Grave E, LeCun Y, Scialom T. Augmented language models: a survey. Transactions on Machine Learning Research, 2023, ISSN:2835-8856

[46] Wang Z, Cheng Z, Zhu H, Fried D, Neubig G. What are tools anyway? A survey from the language model perspective. 2024, arXiv preprint arXiv: 2403.15452

[47] Komeili M, Shuster K, Weston J. Internet-augmented dialogue generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 2022, 8460–8478

[48] Zhang K, Zhang H, Li G, Li J, Li Z, Jin Z. Toolcoder: Teach code generation models to use api search tools. arXiv preprint arXiv:2305.04032, 2023

[49] Shi W, Min S, Yasunaga M, Seo M, James R, Lewis M, Zettlemoyer L, Yih W T. REPLUG: retrieval-augmented black-box language models. In: Proceedings of 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2024, 8371–8384

[50] Paranjape B, Lundberg S, Singh S, Hajishirzi H, Zettlemoyer L, Ribeiro M T. ART: automatic multi-step reasoning and tool-use for large language models. 2023, arXiv preprint arXiv: 2303.09014

[51] Gou Z, Shao Z, Gong Y, Shen Y, Yang Y, Duan N, Chen W. CRITIC: large language models can self-correct with tool-interactive critiquing. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[52] Thoppilan R, De Freitas D, Hall J, Shazeer N, Kulshreshtha A, , . LaMDA: language models for dialog applications. 2022, arXiv preprint arXiv: 2201.08239

[53] Patil S G, Zhang T, Wang X, Gonzalez J E. Gorilla: large language model connected with massive APIs. 2023, arXiv preprint arXiv: 2305.15334

[54] Hao S, Liu T, Wang Z, Hu Z. ToolkenGPT: augmenting frozen language models with massive tools via tool embeddings. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2023, 36

[55] Zhuang Y, Yu Y, Wang K, Sun H, Zhang C. ToolQA: a dataset for LLM question answering with external tools. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2024, 36

[56] Zhang K, Chen H, Li L, Wang W. Syntax error-free and generalizable tool use for LLMS via finite-state decoding. 2024, arXiv preprint arXiv: 2310.07075v1

[57] Gu Y, Shu Y, Yu H, Liu X, Dong Y, Tang J, Srinivasa J, Latapie H, Su Y. Middleware for LLMs: tools are instrumental for language agents in complex environments. 2024, arXiv preprint arXiv: 2402.14672

[58] Cobbe K, Kosaraju V, Bavarian M, Chen M, Jun H, Kaiser L, Plappert M, Tworek J, Hilton J, Nakano R, Hesse C, Schulman J. Training verifiers to solve math word problems. 2021, arXiv preprint arXiv: 2110.14168

[59] Shao Z, Huang F, Huang M. Chaining simultaneous thoughts for numerical reasoning. In: Proceedings of Findings of the Association for Computational Linguistics. 2022, 2533−2547

[60] Kadlčík M, Štefánik M, Sotolar O, Martinek V. Calc-X and calcformers: empowering arithmetical chain-of-thought through interaction with symbolic systems. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 12101−12108

[61] He-Yueya J, Poesia G, Wang R E, Goodman N D. Solving math word problems by combining language models with symbolic solvers. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2023

[62] Zhang B, Zhou K, Wei X, Zhao X, Sha J, Wang S, Wen J R. Evaluating and improving tool-augmented computation-intensive math reasoning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. 2024, 1023

[63] Gou Z, Shao Z, Gong Y, Shen Y, Yang Y, Huang M, Duan N, Chen W. ToRA: a tool-integrated reasoning agent for mathematical problem solving. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[64] Das D, Banerjee D, Aditya S, Kulkarni A. MATHSENSEI: a tool-augmented large language model for mathematical reasoning. In: Proceedings of 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2024, 942–966

[65] Veerendranath V, Shah V, Ghate K. Calc-CMU at semeval-2024 task 7: pre-calc – learning to use the calculator improves numeracy in language models. In: Proceedings of the 18th International Workshop on Semantic Evaluation. 2024, 1468–1475

[66] Bulusu A, Man B, Jagmohan A, Vempaty A, Mari-Wyka J, Akkil D. MathViz-E: A case-study in domain-specialized tool-using agents. 2024, arXiv preprint arXiv: 2407.17544

[67] Gao L, Madaan A, Zhou S, Alon U, Liu P, Yang Y, Callan J, Neubig G. PAL: program-aided language models. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 10764–10799

[68] Chen W, Ma X, Wang X, Cohen W W. Program of thoughts prompting: disentangling computation from reasoning for numerical reasoning tasks. Transactions on Machine Learning Research, 2023, ISSN: 2835-8856

[69] Lu P, Peng B, Cheng H, Galley M, Chang K W, Wu Y N, Zhu S C, Gao J. Chameleon: plug-and-play compositional reasoning with large language models. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2023, 36

[70] Wang X, Peng H, Jabbarvand R, Ji H. LETI: learning to generate from textual interactions. In: Proceedings of Findings of the Association for Computational Linguistics. 2024, 223−239

[71] Wu J, Zhu R, Chen N, Sun Q, Li X, Gao M. Structure-aware fine-tuning for code pre-trained models. In: Proceedings of 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. 2024, 15362−15372

[72] Zhang K, Li J, Li G, Shi X, Jin Z. CodeAgent: enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 13643−13658

[73] Inaba T, Kiyomaru H, Cheng F, Kurohashi S. MultiTool-CoT: GPT-3 can use multiple external tools with chain of thought prompting. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 1522–1532

[74] Bran A M, Cox S, Schilter O, Baldassari C, White A D, Schwaller P. Augmenting large language models with chemistry tools. Nature Machine Intelligence, 2024, 6( 5): 525–535

[75] Ramos M C, Collison C J, White A D. A review of large language models and autonomous agents in chemistry. 2024, arXiv preprint arXiv: 2407.01603

[76] Jin Q, Yang Y, Chen Q, Lu Z. GeneGPT: augmenting large language models with domain tools for improved access to biomedical information. Bioinformatics, 2024, 40( 2): btae075

[77] Theuma A, Shareghi E. Equipping language models with tool use capability for tabular data analysis in finance. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics. 2024, 90–103

[78] Gao S, Wen Y, Zhu M, Wei J, Cheng Y, Zhang Q, Shang S. Simulating financial market via large language model based agents. 2024, arXiv preprint arXiv: 2406.19966

[79] Zhang W, Zhao L, Xia H, Sun S, Sun J, Qin M, Li X, Zhao Y, Zhao Y, Cai X, Zheng L T, Wang X R, An B. A multimodal foundation agent for financial trading: tool-augmented, diversified, and generalist. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024, 4314−4325

[80] Jin Q, Wang Z, Yang Y, Zhu Q, Wright D, Huang T, Wilbur W J, He Z, Taylor A, Chen Q, Lu Z. AgentMD: empowering language agents for risk prediction with large-scale clinical tool learning. 2024, arXiv preprint arXiv: 2402.13225

[81] Li B, Yan T, Pan Y, Luo J, Ji R, Ding J, Xu Z, Liu S, Dong H, Lin Z, Wang Y. MmedAgent: learning to use medical tools with multi-modal agent. 2024, arXiv preprint arXiv: 2407.02483

[82] Yang Z, Li L, Wang J, Lin K, Azarnasab E, Ahmed F, Liu Z, Liu C, Zeng M, Wang L. MM-REACT: prompting chatGPT for multimodal reasoning and action. 2023, arXiv preprint arXiv: 2303.11381

[83] Liu Z, He Y, Wang W, Wang W, Wang Y, Chen S, Zhang Q, Yang Y, Li Q, Yu J, Li K, Chen Z, Yang X, Zhu X, Wang Y, Wang L, Luo P, Dai J, Qiao Y. InternChat: solving vision-centric tasks by interacting with chatbots beyond language. 2023, arXiv preprint arXiv: 2305.05662v2

[84] Gao D, Ji L, Zhou L, Lin K Q, Chen J, Fan Z, Shou M Z. AssistGPT: a general multi-modal assistant that can plan, execute, inspect, and learn. 2023, arXiv preprint arXiv: 2306.08640

[85] Gao Z, Du Y, Zhang X, Ma X, Han W, Zhu S C, Li Q. CLOVA: a closed-loop visual assistant with tool usage and update. In: Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024, 13258−13268

[86] Zhao L, Yang Y, Zhang K, Shao W, Zhang Y, Qiao Y, Luo P, Ji R. DiffAgent: fast and accurate text-to-image API selection with large language model. In: Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024, 6390−6399

[87] Ma Z, Huang W, Zhang J, Gupta T, Krishna R. m&m’s: a benchmark to evaluate tool-use for multi-step multi-modal tasks. 2024, arXiv preprint arXiv: 2403.11085

[88] Wang C, Luo W, Chen Q, Mai H, Guo J, Dong S, Xuan X, Li Z, Ma L, Gao S. Tool-LMM: a large multi-modal model for tool agent learning. 2023, arXiv preprint arXiv: 2401.10727v1

[89] Shen Y, Song K, Tan X, Li D, Lu W, Zhuang Y. HuggingGPT: solving AI tasks with chatGPT and its friends in hugging face. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2024, 36

[90] Lyu B, Cong X, Yu H, Yang P, Qin Y, Ye Y, Lu Y, Zhang Z, Yan Y, Lin Y, Liu Z, Sun M. GitAgent: facilitating autonomous agent with GitHub by tool extension. 2023, arXiv preprint arXiv: 2312.17294

[91] Wei J, Wang X, Schuurmans D, Bosma M, Ichter B, Xia F, Chi E H, Le Q V, Zhou D. Chain-of-thought prompting elicits reasoning in large language models. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 24824–24837

[92] Yao S, Zhao J, Yu D, Du N, Shafran I, Narasimhan K R, Cao Y. ReAct: synergizing reasoning and acting in language models. In: Proceedings of the 11th International Conference on Learning Representations. 2023

[93] Song Y, Xiong W, Zhu D, Li C, Wang K, Tian Y, Li S. RestGPT: connecting large language models with real-world applications via RESTful APIs. 2023, arXiv preprint arXiv: 2306.06624v1

[94] Ruan J, Chen Y, Zhang B, Xu Z, Bao T, Du G, Shi S, Mao H, Zeng X, Zhao R. TPTU: task planning and tool usage of large language model-based AI agents. 2023, arXiv preprint arXiv: 2308.03427v1

[95] Zhuang Y, Chen X, Yu T, Mitra S, Bursztyn V S, Rossi R A, Sarkhel S, Zhang C. ToolChain*: efficient action space navigation in large language models with a* search. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[96] Liu Z, Lai Z, Gao Z, Cui E, Li Z, Zhu X, Lu L, Chen Q, Qiao Y, Dai J, Wang W. ControlLLM: augment language models with tools by searching on graphs. 2023, arXiv preprint arXiv: 2310.17796

[97] Chen Y, Lv A, Lin T E, Chen C, Wu Y, Huang F, Li Y, Yan R. Fortify the shortest stave in attention: enhancing context awareness of large language models for effective tool use. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 11160−11174

[98] Huang T, Jung D, Kumar V, Kachuee M, Li X, Xu P, Chen M. Planning and editing what you retrieve for enhanced tool learning. In: Proceedings of Findings of the Association for Computational Linguistics. 2024, 975−988

[99] Shi Z, Gao S, Chen X, Feng Y, Yan L, Shi H, Yin D, Chen Z, Verberne S, Ren Z. Chain of tools: large language model is an automatic multi-tool learner. 2024, arXiv preprint arXiv: 2405.16533v1

[100] Wu X, Shen Y, Shan C, Song K, Wang S, Zhang B, Feng J, Cheng H, Chen W, Xiong Y, Li D. Can graph learning improve task planning? 2024, arXiv preprint arXiv: 2405.19119v1

[101] Liu Y, Yuan Y, Wang C, Han J, Ma Y, Zhang L, Zheng N, Xu H. From summary to action: enhancing large language models for complex tasks with open world APIs. 2024, arXiv preprint arXiv: 2402.18157

[102] Zheng Y, Li P, Yan M, Zhang J, Huang F, Liu Y. Budget-constrained tool learning with planning. In: Proceedings of Findings of the Association for Computational Linguistics ACL 2024. 2024, 9039−9052

[103] Qu C, Dai S, Wei X, Cai H, Wang S, Yin D, Xu J, Wen J R. From exploration to mastery: enabling LLMs to master tools via self-driven interactions. 2024, arXiv preprint arXiv: 2410.08197

[104] Liang Y, Wu C, Song T, Wu W, Xia Y, Liu Y, Ou Y, Lu S, Ji L, Mao S, Wang Y, Shou L, Gong M, Duan N. Taskmatrix. AI: Completing tasks by connecting foundation models with millions of APIs. Intelligent Computing, 2024, 3: 0063

[105] Qian C, Xiong C, Liu Z, Liu Z. Toolink: linking toolkit creation and using through chain-of-solving on open-source model. In: Proceedings of 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2024, 831−854

[106] Kong Y, Ruan J, Chen Y, Zhang B, Bao T, Shi S, Du G, Hu X, Mao H, Li Z, Zeng X, Zhao R. TPTU-v2: boosting task planning and tool usage of large language model-based agents in real-world systems. 2023, arXiv preprint arXiv: 2311.11315

[107] Shen W, Li C, Chen H, Yan M, Quan X, Chen H, Zhang J, Huang F. Small LLMs are weak tool learners: a multi-LLM agent. 2024, arXiv preprint arXiv: 2401.07324

[108] Gao S, Dwivedi-Yu J, Yu P, Tan X E, Pasunuru R, Golovneva O, Sinha K, Celikyilmaz A, Bosselut A, Wang T. Efficient tool use with chain-of-abstraction reasoning. 2024, arXiv preprint arXiv: 2401.17464

[109] Gui A, Li J, Dai Y, Du N, Xiao H. Look before you leap: towards decision-aware and generalizable tool-usage for large language models. 2024, arXiv preprint arXiv: 2402.16696

[110] Ge Y, Hua W, Mei K, Tan J, Xu S, Li Z, Zhang Y. OpenAGI: when LLM meets domain experts. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2023, 36

[111] Wang Y, Yu J, Yao Z, Zhang J, Xie Y, Tu S, Fu Y, Feng Y, Zhang J, Zhang J, Huang B, Li Y, Yuan H, Hou L, Li J, Tang J. A solution-based LLM API-using methodology for academic information seeking. 2024, arXiv preprint arXiv: 2405.15165

[112] Chen S, Wang Y, Wu Y F, Chen Q G, Xu Z, Luo W, Zhang K, Zhang L. Advancing tool-augmented large language models: integrating insights from errors in inference trees. 2024, arXiv preprint arXiv: 2406.07115

[113] Liu Z, Hoang T, Zhang J, Zhu M, Lan T, Kokane S, Tan J, Yao W, Liu Z, Feng Y, Murthy R, Yang L, Savarese S, Niebles J C, Wang H, Heinecke S, Xiong C. APIGen: automated pipeline for generating verifiable and diverse function-calling datasets. 2024, arXiv preprint arXiv: 2406.18518

[114] Sparck Jones K. A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 1972, 28( 1): 11–21

[115] Robertson S, Zaragoza H. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends® in Information Retrieval, 2009, 3( 4): 333–389

[116] Reimers N, Gurevych I. Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019, 3982–3992

[117] Xiong L, Xiong C, Li Y, Tang K F, Liu J, Bennett P N, Ahmed J, Overwijk A. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In: Proceedings of the 9th International Conference on Learning Representations. 2021

[118] Hofstätter S, Lin S C, Yang J H, Lin J, Hanbury A. Efficiently teaching an effective dense retriever with balanced topic aware sampling. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2021, 113–122

[119] Izacard G, Caron M, Hosseini L, Riedel S, Bojanowski P, Joulin A, Grave E. Unsupervised dense information retrieval with contrastive learning. Transactions on Machine Learning Research, 2022, ISSN: 2385-8856

[120] Gao L, Callan J. Unsupervised corpus aware language model pre-training for dense passage retrieval. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. 2022, 2843–2853

[121] Yuan L, Chen Y, Wang X, Fung Y R, Peng H, Ji H. CRAFT: customizing LLMs by creating and retrieving from specialized toolsets. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[122] Anantha R, Bandyopadhyay B, Kashi A, Mahinder S, Hill A W, Chappidi S. ProTIP: progressive tool retrieval improves planning. 2023, arXiv preprint arXiv: 2312.10332

[123] Zheng Y, Li P, Liu W, Liu Y, Luan J, Wang B. ToolRerank: adaptive and hierarchy-aware reranking for tool retrieval. In: Proceedings of 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. 2024, 16263−16273

[124] Qu C, Dai S, Wei X, Cai H, Wang S, Yin D, Xu J, Wen J R. Towards completeness-oriented tool retrieval for large language models. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. 2024, 1930–1940

[125] Chen Z, Zhou K, Zhang B, Gong Z, Zhao X, Wen J R. ChatCoT: tool-augmented chain-of-thought reasoning on chat-based large language models. In: Proceedings of Findings of the Association for Computational Linguistics: EMNLP 2023, 2023, 14777−14790

[126] Liu X, Peng Z, Yi X, Xie X, Xiang L, Liu Y, Xu D. ToolNet: connecting large language models with massive tools via tool graph. 2024, arXiv preprint arXiv: 2403.00839

[127] Mekala D, Weston J, Lanchantin J, Raileanu R, Lomeli M, Shang J, Dwivedi-Yu J. TOOLVERIFIER: generalization to new tools via self-verification. 2024, arXiv preprint arXiv: 2402.14158

[128] Qiao S, Gui H, Lv C, Jia Q, Chen H, Zhang N. Making language models better tool learners with execution feedback. In: Proceedings of 2024 Conference of the North American Chapter of the Association for Computational Linguistics. 2024, 3550−3568

[129] Du Y, Wei F, Zhang H. AnyTool: self-reflective, hierarchical agents for large-scale API calls. In: Proceedings of the 41st International Conference on Machine Learning. 2024

[130] Fore M, Singh S, Stamoulis D. GeckOpt: LLM system efficiency via intent-based tool selection. In: Proceedings of Great Lakes Symposium on VLSI 2024. 2024, 353−354

[131] Zhang Y, Cai H, Song X, Chen Y, Sun R, Zheng J. Reverse chain: a generic-rule for LLMs to master multi-API planning. In: Proceedings of Findings of the Association for Computational Linguistics. 2024, 302−325

[132] Yuan S, Song K, Chen J, Tan X, Shen Y, Kan R, Li D, Yang D. EASYTOOL: enhancing LLM-based agents with concise tool instruction. 2024, arXiv preprint arXiv: 2401.06201

[133] Shi Z, Gao S, Chen X, Feng Y, Yan L, Shi H, Yin D, Ren P, Verberne S, Ren Z. Learning to use tools via cooperative and interactive agents. 2024, arXiv preprint arXiv: 2403.03031v4

[134] Yang R, Song L, Li Y, Zhao S, Ge Y, Li X, Shan Y. GPT4Tools: teaching large language model to use tools via self-instruction. In: Proceedings of the 37th Conference on Neural Information Processing Systems. 2023, 36

[135] Li L, Chai Y, Wang S, Sun Y, Tian H, Zhang N, Wu H. Tool-augmented reward modeling. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[136] Wang B, Fang H, Eisner J, Van Durme B, Su Y. LLMs in the imaginarium: tool learning through simulated trial and error. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024,10583−10604

[137] Xu F, Shi W, Choi E. RECOMP: improving retrieval-augmented LMS with compression and selective augmentation. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[138] Ye J, Li G, Gao S, Huang C, Wu Y, Li S, Fan X, Dou S, Zhang Q, Gui T, Huang X. ToolEyes: fine-grained evaluation for tool learning capabilities of large language models in real-world scenarios. 2024, arXiv preprint arXiv: 2401.00741

[139] Huang S, Zhong W, Lu J, Zhu Q, Gao J, Liu W, Hou Y, Zeng X, Wang Y, Shang L, Jiang X, Xu R, Liu Q. Planning, creation, usage: benchmarking LLMs for comprehensive tool utilization in real-world complex scenarios. In: Proceedings of Findings of the Association for Computational Linguistics ACL 2024. 2024, 4363−4400

[140] Wu M, Zhu T, Han H, Tan C, Zhang X, Chen W. Seal-tools: self-instruct tool learning dataset for agent tuning and detailed benchmark. 2024, arXiv preprint arXiv: 2405.08355v1

[141] Basu K, Abdelaziz I, Chaudhury S, Dan S, Crouse M, Munawar A, Austel V, Kumaravel S, Muthusamy V, Kapanipathi P, Lastras L A. API-BLEND: a comprehensive corpora for training and benchmarking API LLMs. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 12859−12870

[142] Shen H, Li Y, Meng D, Cai D, Qi S, Zhang L, Xu M, Ma Y. ShortcutsBench: a large-scale real-world benchmark for API-based agents. 2024, arXiv preprint arXiv: 2407.00132v2

[143] Wang J, Ma Z, Li Y, Zhang S, Chen C, Chen K, Le X. GTA: a benchmark for general tool agents. 2024, arXiv preprint arXiv: 2407.08713

[144] Ning K, Su Y, Lv X, Zhang Y, Liu J, Liu K, Xu J. WTU-EVAL: a whether-or-not tool usage evaluation benchmark for large language models. 2024, arXiv preprint arXiv: 2407.12823

[145] Trivedi H, Khot T, Hartmann M, Manku R, Dong V, Li E, Gupta S, Sabharwal A, Balasubramanian N. AppWorld: a controllable world of apps and people for benchmarking interactive coding agents. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 16022−16076

[146] Ruan Y, Dong H, Wang A, Pitis S, Zhou Y, Ba J, Dubois Y, Maddison C J, Hashimoto T. Identifying the risks of lm agents with an lm-emulated sandbox. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[147] Farn N, Shin R. ToolTalk: evaluating tool-usage in a conversational setting. 2023, arXiv preprint arXiv: 2311.10775

[148] Zhong Y, Qi M, Wang R, Qiu Y, Zhang Y, Ma H. VioTGPT: learning to schedule vision tools towards intelligent video internet of things. 2023, arXiv preprint arXiv: 2312.00401

[149] Ye J, Wu Y, Gao S, Huang C, Li S, Li G, Fan X, Zhang Q, Gui T, Huang X. RoTBench: a multi-level benchmark for evaluating the robustness of large language models in tool learning. 2024, arXiv preprint arXiv: 2401.08326

[150] Ye J, Li S, Li G, Huang C, Gao S, Wu Y, Zhang Q, Gui T, Huang X. ToolSword: unveiling safety issues of large language models in tool learning across three stages. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. 2024, 2181−2211

[151] Ma Y, Gou Z, Hao J, Xu R, Wang S, Pan L, Yang Y, Cao Y, Sun A, Awadalla H, Chen W. SciAgent: Tool-augmented language models for scientific reasoning. 2024, arXiv preprint arXiv: 2402.11451

[152] Guo Z, Cheng S, Wang H, Liang S, Qin Y, Li P, Liu Z, Sun M, Liu Y. StableToolBench: towards stable large-scale benchmarking on tool learning of large language models. In: Proceedings of Findings of the Association for Computational Linguistics ACL 2024. 2024, 11143−11156

[153] Zhan Q, Liang Z, Ying Z, Kang D. InjecAgent: benchmarking indirect prompt injections in tool-integrated large language model agents. In: Proceedings of Findings of the Association for Computational Linguistics ACL 2024. 2024, 10471−10506

[154] Guo Z, Huang Y, Xiong D. CToolEval: a Chinese benchmark for LLM-powered agent evaluation in real-world API interactions. In: Proceedings of Findings of the Association for Computational Linguistics ACL 2024. 2024, 15711−15724

[155] Lu J, Holleis T, Zhang Y, Aumayer B, Nan F, Bai F, Ma S, Ma S, Li M, Yin G, Wang Z, Pang R. ToolSandbox: a stateful, conversational, interactive evaluation benchmark for LLM tool use capabilities. 2024, arXiv preprint arXiv: 2408.04682

[156] Zhu M. Recall, precision and average precision. University of Waterloo, Dissertation, 2004, 6

[157] Järvelin K, Kekäläinen J. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS), 2002, 20( 4): 422–446

[158] Papineni K, Roukos S, Ward T, Zhu W J. Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. 2002, 311–318

[159] Lin C Y. ROUGE: a package for automatic evaluation of summaries. In: Proceedings of Text Summarization Branches Out. 2004, 74–81

[160] Blackwell M, Iacus S, King G, Porro G. CEM: coarsened exact matching in Stata. The Stata Journal: Promoting communications on statistics and Stata, 2009, 9( 4): 524–546

[161] Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, Schulman J, Hilton J, Kelton F, Miller L, Simens M, Askell A, Welinder P, Christiano P, Leike J, Lowe R. Training language models to follow instructions with human feedback. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 2011

[162] Dao X Q, Le N B. Investigating the effectiveness of chatGPT in mathematical reasoning and problem solving: evidence from the Vietnamese national high school graduation examination. 2023, arXiv preprint arXiv: 2306.06331

[163] Wei T, Luan J, Liu W, Dong S, Wang B. CMATH: can your language model pass Chinese elementary school math test? 2023, arXiv preprint arXiv: 2306.16636

[164] Chen M, Tworek J, Jun H, Yuan Q, de Oliveira Pinto H P, , . Evaluating large language models trained on code. 2021, arXiv preprint arXiv: 2107.03374

[165] Austin J, Odena A, Nye M, Bosma M, Michalewski H, Dohan D, Jiang E, Cai C, Terry M, Le Q, Sutton C. Program synthesis with large language models. 2021, arXiv preprint arXiv: 2108.07732

[166] Singh S, Fore M, Stamoulis D. Evaluating tool-augmented agents in remote sensing platforms. 2024, arXiv preprint arXiv: 2405.00709v1

[167] Linardatos P, Papastefanopoulos V, Kotsiantis S. Explainable AI: a review of machine learning interpretability methods. Entropy, 2021, 23( 1): 18

[168] Zhao H, Chen H, Yang F, Liu N, Deng H, Cai H, Wang S, Yin D, Du M. Explainability for large language models: a survey. ACM Transactions on Intelligent Systems and Technology, 2024, 15( 2): 20

[169] Weidinger L, Mellor J, Rauh M, Griffin C, Uesato J, , . Ethical and social risks of harm from language models. 2021, arXiv preprint arXiv: 2112.04359

[170] Gao T, Yen H, Yu J, Chen D. Enabling large language models to generate text with citations. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 6465–6488

[171] Sun H, Cai H, Wang B, Hou Y, Wei X, Wang S, Zhang Y, Yin D. Towards verifiable text generation with evolving memory and self-reflection. 2024, arXiv preprint arXiv: 2312.09075

[172] Wallace E, Feng S, Kandpal N, Gardner M, Singh S. Universal adversarial triggers for attacking and analyzing NLP. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019, 2153–2162

[173] Jin D, Jin Z, Zhou J T, Szolovits P. Is Bert really robust? A strong baseline for natural language attack on text classification and entailment. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence. 2020, 8018–8025

[174] Wu F, Zhang N, Jha S, McDaniel P, Xiao C. A new era in LLM security: exploring security concerns in real-world LLM-based systems. 2024, arXiv preprint arXiv: 2402.18649

[175] Zhang J. Graph-toolFormer: to empower LLMs with graph reasoning ability via prompt augmented by chatGPT. 2023, arXiv preprint arXiv: 2304.11116

[176] Li C, Yang R, Li T, Bafarassat M, Sharifi K, Bergemann D, Yang Z. STRIDE: a tool-assisted LLM agent framework for strategic and interactive decision-making. 2024, arXiv preprint arXiv: 2405.16376

[177] Huang W, Abbeel P, Pathak D, Mordatch I. Language models as zero-shot planners: extracting actionable knowledge for embodied agents. In: Proceedings of the 39th International Conference on Machine Learning. 2022, 9118–9147

[178] Chern I C, Chern S, Chen S, Yuan W, Feng K, Zhou C, He J, Neubig G, Liu P. FacTool: factuality detection in generative AI–a tool augmented framework for multi-task and multi-domain scenarios. 2023, arXiv preprint arXiv: 2307.13528

[179] Xu S, Pang L, Shen H, Cheng X, Chua T S. Search-in-the-chain: interactively enhancing large language models with search for knowledge-intensive tasks. In: Proceedings of ACM Web Conference 2024. 2024, 1362–1373

[180] Kim G, Baldi P, McAleer S. Language models can solve computer tasks. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. 2024, 1723

[181] Liu Y, Peng X, Zhang Y, Cao J, Zhang X, Cheng S, Wang X, Yin J, Du T. Tool-planner: dynamic solution tree planning for large language model with tool clustering. 2024, arXiv preprint arXiv: 2406.03807v1

[182] Erbacher P, Falissard L, Guigue V, Soulier L. Navigating uncertainty: optimizing API dependency for hallucination reduction in closed-book QA. In: Proceedings of the 46th European Conference on Information Retrieval. 2024, 393–402

[183] Xu Q, Li Y, Xia H, Li W. Enhancing tool retrieval with iterative feedback from large language models. 2024, arXiv preprint arXiv: 2406.17465

[184] Xiao S, Liu Z, Zhang P, Muennighoff N. C-pack: Pack-aged resources to advance general chinese embedding, 2023

[185] Gemini Team Google. Gemini: a family of highly capable multimodal models. 2024, arXiv preprint arXiv: 2312.11805

[186] Hsieh C Y, Chen S A, Li C L, Fujii Y, Ratner A, Lee C Y, Krishna R, Pfister T. Tool documentation enables zero-shot tool-usage with large language models. 2023, arXiv preprint arXiv: 2308.00675

[187] Xu Y, Feng Y, Mu H, Hou Y, Li Y, Wang X, Zhong W, Li Z, Tu D, Zhu Q, Zhang M, Che W. Concise and precise context compression for tool-using language models. In: Proceedings of Findings of the Association for Computational Linguistics ACL 2024. 2024, 16430−16441

[188] Shen Y, Song K, Tan X, Zhang W, Ren K, Yuan S, Lu W, Li D, Zhuang Y. TaskBench: benchmarking large language models for task automation. 2023, arXiv preprint arXiv: 2311.18760

[189] Wang H, Wang H, Wang L, Hu M, Wang R, Xue B, Lu H, Mi F, Wong K F. TPE: towards better compositional reasoning over conceptual tools with multi-persona collaboration. 2023, arXiv preprint arXiv: 2309.16090

[190] Qian C, Han C, Fung Y, Qin Y, Liu Z, Ji H. CREATOR: tool creation for disentangling abstract and concrete reasoning of large language models. In: Proceedings of Findings of Association for Computational Linguistics: EMNLP 2023. 2023, 6922–6939

[191] Jacovi A, Caciularu A, Herzig J, Aharoni R, Bohnet B, Geva M. A comprehensive evaluation of tool-assisted generation strategies. In: Proceedings of Findings of Findings of the Association for Computational Linguistics: EMNLP 2023. 2023, 13856−13878

[192] Nathani D, Wang D, Pan L, Wang W Y. MAF: multi-aspect feedback for improving reasoning in large language models. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 6591−6616

[193] Yao Y, Duan J, Xu K, Cai Y, Sun Z, Zhang Y. A survey on large language model (LLM) security and privacy: the good, the bad, and the ugly. High-Confidence Computing, 2024, 4: 100211

[194] Cui T, Wang Y, Fu C, Xiao Y, Li S, Deng X, Liu Y, Zhang Q, Qiu Z, Li P, Tan Z, Xiong J, Kong X, Wen Z, Xu K, Li Q. Risk taxonomy, mitigation, and assessment benchmarks of large language model systems. 2024, arXiv preprint arXiv: 2401.05778

[195] Das B C, Amini M H, Wu Y. Security and privacy challenges of large language models: a survey. 2024, arXiv preprint arXiv: 2402.00888

[196] Qin Y, Cai Z, Jin D, Yan L, Liang S, Zhu K, Lin Y, Han X, Ding N, Wang H, Xie R, Qi F, Liu Z, Sun M, Zhou J. WebCPM: interactive web search for Chinese long-form question answering. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. 2023, 8968−8988

[197] Miao X, Oliaro G, Zhang Z, Cheng X, Jin H, Chen T, Jia Z. Towards efficient generative large language model serving: a survey from algorithms to systems. 2023, arXiv preprint arXiv: 2312.15234

[198] Cai T, Wang X, Ma T, Chen X, Zhou D. Large language models as tool makers. In: Proceedings of the 12th International Conference on Learning Representations. 2024

[199] Wang Z, Neubig G, Fried D. TroVE: inducing verifiable and efficient toolboxes for solving programmatic tasks. In: Proceedings of the 41st International Conference on Machine Learning. 2024, 51177−51191

Acknowledgements

This work was funded by the National Key R&D Program of China (2023YFA1008704), the National Natural Science Foundation of China (Grant No. 62377044), Beijing Key Laboratory of Big Data Management and Analysis Methods, Major Innovation & Planning Interdisciplinary Platform for the “Double-First Class” Initiative, funds for building world-class universities (disciplines) of Renmin University of China, and PCC@RUC. The authors would like to extend their sincere gratitude to Yankai Lin for his constructive feedback throughout the development of this work.

Competing interests

The authors declare that they have no competing interests or financial conflicts to disclose.

RIGHTS & PERMISSIONS

2025 Higher Education Press