{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:33Z","timestamp":1777890153325,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92467204,62472249,62402264"],"award-info":[{"award-number":["92467204,62472249,62402264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00814","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8699-8709","source":"Crossref","is-referenced-by-count":0,"title":["CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning"],"prefix":"10.1109","author":[{"given":"Duo","family":"Wu","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghe","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Meng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Sun","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Agarwal"},{"key":"ref3","article-title":"Finbert: Financial sentiment analysis with pretrained language models","author":"Araci","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"3658","article-title":"Guiding LLMs the right way: Fast, non-invasive constrained generation","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Beurer-Kellner"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2025.101260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2314"},{"key":"ref9","first-page":"669","article-title":"Swin2sr: Swinv2 transformer for compressed image super-resolution and restoration","volume-title":"European Conference on Computer Vision","author":"Marcos"},{"key":"ref10","article-title":"An image is worth $16 x 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref13","article-title":"Assistgpt: A general multi-modal assistant that can plan, execute, inspect, and learn","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01259"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0242"},{"key":"ref16","article-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1988"},{"key":"ref19","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Edward"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"ref21","article-title":"Can 11 ms effectively leverage graph structural information through prompts, and why?","author":"Huang","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref22","article-title":"Qwen2.5-coder technical report","author":"Hui","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","volume-title":"Function as a service market size & share analysis - growth trends & forecasts","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref26","volume-title":"AWS Lambda. Run code without thinking about servers","year":"2024"},{"key":"ref27","article-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Formal-llm: Integrating formal language and natural language for controllable 11 m -based agents","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_8"},{"key":"ref31","article-title":"Interngpt: Solving vision-centric tasks by interacting with chatgpt beyond language","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_6"},{"key":"ref33","article-title":"Toolsandbox: A stateful, conversational, interactive evaluation benchmark for llm tool use capabilities","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref35","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume":"36","author":"Lu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","volume-title":"OpenAI. Chatgpt","year":"2024"},{"key":"ref37","article-title":"Art: Automatic multi-step reasoning and tool-use for large language models","author":"Paranjape","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","author":"Shishir","year":"2024","journal-title":"Gorilla: Large language model connected with massive APIs"},{"key":"ref39","article-title":"Let your graph do the talking: Encoding structured data for 11 ms","author":"Perozzi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.195"},{"issue":"140","key":"ref41","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref42","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2997"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358296"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1657"},{"key":"ref46","article-title":"Taskbench: Benchmarking large language models for task automation","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Structuredrag: Json response formatting with large language models","author":"Shorten","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref49","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Gta: A benchmark for general tool agents","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref52","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672268"},{"key":"ref54","article-title":"Mathchat: Converse to tackle challenging math problems with 11m agents","volume-title":"ICLR 2024 Workshop on Large Language Model Agents","author":"Wu","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3149"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref57","article-title":"Mm-react: Prompting chatgpt for multi-modal reasoning and action","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Open-domain implicit format control for large language model generation","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1023"},{"key":"ref61","article-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073703"},{"key":"ref63","article-title":"Bertscore: Evaluating text generation with bert","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhang","year":"2020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2180"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443307.pdf?arnumber=11443307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:21Z","timestamp":1777613301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00814","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}