Growing interest in Artificial Intelligence (AI) has resulted in a surge in demand for faster methods of Machine Learning (ML) model training and inference. This demand for speed has prompted the use of high performance computing (HPC) systems that excel in managing distributed workloads. Because data is the main fuel for AI applications, the performance of the storage and I/O subsystem of HPC systems is critical. In the past, HPC applications accessed large portions of data written by simulations or experiments or ingested data for visualizations or analysis tasks. ML workloads perform small reads spread across a large number of random files. This shift of I/O access patterns poses several challenges to modern parallel storage systems. In this paper, we survey I/O in ML applications on HPC systems, and target literature within a 6-year time window from 2019 to 2024. We define the scope of the survey, provide an overview of the common phases of ML, review available profilers and benchmarks, examine the I/O patterns encountered during offline data preparation, training, and inference, and explore I/O optimizations utilized in modern ML frameworks and proposed in recent literature. Lastly, we seek to expose research gaps that could spawn further R&D.
{"title":"I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey","authors":"Noah Lewis, Jean Luca Bez, Surendra Byna","doi":"10.1145/3722215","DOIUrl":"https://doi.org/10.1145/3722215","url":null,"abstract":"Growing interest in Artificial Intelligence (AI) has resulted in a surge in demand for faster methods of Machine Learning (ML) model training and inference. This demand for speed has prompted the use of high performance computing (HPC) systems that excel in managing distributed workloads. Because data is the main fuel for AI applications, the performance of the storage and I/O subsystem of HPC systems is critical. In the past, HPC applications accessed large portions of data written by simulations or experiments or ingested data for visualizations or analysis tasks. ML workloads perform small reads spread across a large number of random files. This shift of I/O access patterns poses several challenges to modern parallel storage systems. In this paper, we survey I/O in ML applications on HPC systems, and target literature within a 6-year time window from 2019 to 2024. We define the scope of the survey, provide an overview of the common phases of ML, review available profilers and benchmarks, examine the I/O patterns encountered during offline data preparation, training, and inference, and explore I/O optimizations utilized in modern ML frameworks and proposed in recent literature. Lastly, we seek to expose research gaps that could spawn further R&D.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"47 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artificial Intelligence (AI) applications critically depend on data. Poor quality data produces inaccurate and ineffective AI models that may lead to incorrect or unsafe use. Evaluation of data readiness is a crucial step in improving the quality and appropriateness of data usage for AI. R&D efforts have been spent on improving data quality. However, standardized metrics for evaluating data readiness for use in AI training are still evolving. In this study, we perform a comprehensive survey of metrics used to verify data readiness for AI training. This survey examines more than 140 papers published by ACM Digital Library, IEEE Xplore, journals such as Nature, Springer, and Science Direct, and online articles published by prominent AI experts. This survey aims to propose a taxonomy of data readiness for AI (DRAI) metrics for structured and unstructured datasets. We anticipate that this taxonomy will lead to new standards for DRAI metrics that would be used for enhancing the quality, accuracy, and fairness of AI training and inference.
{"title":"Data Readiness for AI: A 360-Degree Survey","authors":"Kaveen Hiniduma, Suren Byna, Jean Luca Bez","doi":"10.1145/3722214","DOIUrl":"https://doi.org/10.1145/3722214","url":null,"abstract":"Artificial Intelligence (AI) applications critically depend on data. Poor quality data produces inaccurate and ineffective AI models that may lead to incorrect or unsafe use. Evaluation of data readiness is a crucial step in improving the quality and appropriateness of data usage for AI. R&D efforts have been spent on improving data quality. However, standardized metrics for evaluating data readiness for use in AI training are still evolving. In this study, we perform a comprehensive survey of metrics used to verify data readiness for AI training. This survey examines more than 140 papers published by ACM Digital Library, IEEE Xplore, journals such as Nature, Springer, and Science Direct, and online articles published by prominent AI experts. This survey aims to propose a taxonomy of data readiness for AI (DRAI) metrics for structured and unstructured datasets. We anticipate that this taxonomy will lead to new standards for DRAI metrics that would be used for enhancing the quality, accuracy, and fairness of AI training and inference.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"18 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vehicles traveling through cities generate extensive vehicle trajectory collected by scalable sensors, providing excellent opportunities to address urban challenges such as traffic congestion and public safety. In this survey, we systematically review vehicle trajectory collection, preprocessing, analytics, and applications. First, we focus on the standard techniques for vehicle trajectory collection and corresponding datasets. Next, we introduce representative approaches for the latest advances in vehicle trajectory processing. We further discuss individual travel behavior and collective mobility analytics using vehicle trajectory. Since private cars constitute the majority of urban vehicles and form the basis for many recent research findings, we emphasize analytics based on private car trajectory data. We then compile vehicle trajectory-boosted applications from the perspective of computing vehicle trajectory. Finally, we go through unresolved problems with vehicle trajectory and outline potential future research directions.
{"title":"Vehicle Trajectory Data Processing, Analytics, and Applications: A Survey","authors":"Chenxi Liu, Zhu Xiao, Wangchen Long, Tong Li, Hongbo Jiang, Keqin Li","doi":"10.1145/3715902","DOIUrl":"https://doi.org/10.1145/3715902","url":null,"abstract":"Vehicles traveling through cities generate extensive vehicle trajectory collected by scalable sensors, providing excellent opportunities to address urban challenges such as traffic congestion and public safety. In this survey, we systematically review vehicle trajectory collection, preprocessing, analytics, and applications. First, we focus on the standard techniques for vehicle trajectory collection and corresponding datasets. Next, we introduce representative approaches for the latest advances in vehicle trajectory processing. We further discuss individual travel behavior and collective mobility analytics using vehicle trajectory. Since private cars constitute the majority of urban vehicles and form the basis for many recent research findings, we emphasize analytics based on private car trajectory data. We then compile vehicle trajectory-boosted applications from the perspective of computing vehicle trajectory. Finally, we go through unresolved problems with vehicle trajectory and outline potential future research directions.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"37 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143569496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marloes Vredenborg, Anouk van Kasteren, Judith Masthoff
In recent years, efforts to promote public transport usage have emphasized the integration of personalization into passenger information systems. Whilst numerous studies have explored this topic, a comprehensive overview of the state-of-the-art remains absent. To address this gap, we systematically reviewed 91 research papers published between 2000 and October 2024. Based on our review, we introduce a comprehensive framework that organizes the field along three key dimensions: personalization objects, attributes, and evaluation. Furthermore, we provide valuable insights for researchers and practitioners engaged in the study, design, and development of personalized passenger information systems and identify research opportunities to guide future advancements in the field.
{"title":"Personalization in Public Transport Passenger Information Systems: A Systematic Review and Framework","authors":"Marloes Vredenborg, Anouk van Kasteren, Judith Masthoff","doi":"10.1145/3721478","DOIUrl":"https://doi.org/10.1145/3721478","url":null,"abstract":"In recent years, efforts to promote public transport usage have emphasized the integration of personalization into passenger information systems. Whilst numerous studies have explored this topic, a comprehensive overview of the state-of-the-art remains absent. To address this gap, we systematically reviewed 91 research papers published between 2000 and October 2024. Based on our review, we introduce a comprehensive framework that organizes the field along three key dimensions: personalization objects, attributes, and evaluation. Furthermore, we provide valuable insights for researchers and practitioners engaged in the study, design, and development of personalized passenger information systems and identify research opportunities to guide future advancements in the field.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"191 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143569738","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine learning techniques for cybersecurity-related software engineering tasks are becoming increasingly popular. The representation of source code is a key portion of the technique that can impact the way the model is able to learn the features of the source code. With an increasing number of these techniques being developed, it is valuable to see the current state of the field to better understand what exists and what’s not there yet. This paper presents a study of these existing ML-based approaches and demonstrates what type of representations were used for different cybersecurity tasks and programming languages. Additionally, we study what types of models are used with different representations. We have found that graph-based representations are the most popular category of representation, and Tokenizers and Abstract Syntax Trees (ASTs) are the two most popular representations overall ( e.g. , AST and Tokenizers are the representations with the highest count of papers, while graph-based representations is the category with the highest count of papers). We also found that the most popular cybersecurity task is vulnerability detection, and the language that is covered by the most techniques is C. Finally, we found that sequence-based models are the most popular category of models, and Support Vector Machines (SVMs) are the most popular model overall.
{"title":"A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Tasks","authors":"Beatrice Casey, Joanna C. S. Santos, George Perry","doi":"10.1145/3721977","DOIUrl":"https://doi.org/10.1145/3721977","url":null,"abstract":"Machine learning techniques for cybersecurity-related software engineering tasks are becoming increasingly popular. The representation of source code is a key portion of the technique that can impact the way the model is able to learn the features of the source code. With an increasing number of these techniques being developed, it is valuable to see the current state of the field to better understand what exists and what’s not there yet. This paper presents a study of these existing ML-based approaches and demonstrates what type of representations were used for different cybersecurity tasks and programming languages. Additionally, we study what types of models are used with different representations. We have found that graph-based representations are the most popular category of representation, and Tokenizers and Abstract Syntax Trees (ASTs) are the two most popular representations overall ( <jats:italic>e.g.</jats:italic> , AST and Tokenizers are the representations with the highest count of papers, while graph-based representations is the category with the highest count of papers). We also found that the most popular cybersecurity task is vulnerability detection, and the language that is covered by the most techniques is C. Finally, we found that sequence-based models are the most popular category of models, and Support Vector Machines (SVMs) are the most popular model overall.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"28 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they can potentially be. Recent studies have shown that DMs are prone to a wide range of attacks, including adversarial attacks, membership inference attacks, backdoor injection, and various multi-modal threats. Since numerous pre-trained DMs are published widely on the Internet, potential threats from these attacks are especially detrimental to the society, making DM-related security a topic worthy of investigation. Therefore, in this paper, we conduct a comprehensive survey on the security aspect of DMs, focusing on various attack and defense methods for DMs. First, we present crucial knowledge of DMs with five main types of DMs, including denoising diffusion probabilistic models, denoising diffusion implicit models, noise conditioned score networks, stochastic differential equations, and multi-modal conditional DMs. We provide a comprehensive survey of recent works investigating different types of attacks that exploit the vulnerabilities of DMs. Then, we thoroughly review potential countermeasures to mitigate each of the presented threats. Finally, we discuss open challenges of DM-related security and describe potential research directions for this topic.
{"title":"Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey","authors":"Vu Tuan Truong, Luan Ba Dang, Long Bao Le","doi":"10.1145/3721479","DOIUrl":"https://doi.org/10.1145/3721479","url":null,"abstract":"Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they can potentially be. Recent studies have shown that DMs are prone to a wide range of attacks, including adversarial attacks, membership inference attacks, backdoor injection, and various multi-modal threats. Since numerous pre-trained DMs are published widely on the Internet, potential threats from these attacks are especially detrimental to the society, making DM-related security a topic worthy of investigation. Therefore, in this paper, we conduct a comprehensive survey on the security aspect of DMs, focusing on various attack and defense methods for DMs. First, we present crucial knowledge of DMs with five main types of DMs, including denoising diffusion probabilistic models, denoising diffusion implicit models, noise conditioned score networks, stochastic differential equations, and multi-modal conditional DMs. We provide a comprehensive survey of recent works investigating different types of attacks that exploit the vulnerabilities of DMs. Then, we thoroughly review potential countermeasures to mitigate each of the presented threats. Finally, we discuss open challenges of DM-related security and describe potential research directions for this topic.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"10 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143546525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiahua Huang, Weiwei Lin, Wentai Wu, Yang Wang, Haocheng Zhong, Xinhua Wang, Keqin Li
The effective and efficient utilization of AI accelerators represents a critical issue for the practitioners engaged in the field of deep learning. Practical evidence from companies such as Alibaba, SenseTime, and Microsoft reveals that the utilization of production GPU clusters in the industry is generally between 25% and 50%. This indicates a significant opportunity for improvement. To this end, AI accelerator resource sharing has emerged as a promising approach to the performance optimization of multi-tenant clusters. This survey covers this line of studies from 2016 to 2024, focusing primarily on system efficiency while also including discussion on fairness, interference, and security in AI accelerator sharing. We revisit the fundamentals and key concepts, followed by a comprehensive review of recent advances in the field. We find that over 70% of the studies focus on efficiency improvement. We also observe that approximately half of the reviewed studies have made their source code publicly available, while fewer than one-third of the studies did not utilize a physical machine for experimentation. Finally, based on the limitations of existing research, we outline several directions for future research concerning the integration of sharing with large language models (LLMs), coordination between schedulers and application-layer metrics, and collaboration among heterogeneous accelerators.
{"title":"On Efficiency, Fairness and Security in AI Accelerator Resource Sharing: A Survey","authors":"Jiahua Huang, Weiwei Lin, Wentai Wu, Yang Wang, Haocheng Zhong, Xinhua Wang, Keqin Li","doi":"10.1145/3721427","DOIUrl":"https://doi.org/10.1145/3721427","url":null,"abstract":"The effective and efficient utilization of AI accelerators represents a critical issue for the practitioners engaged in the field of deep learning. Practical evidence from companies such as Alibaba, SenseTime, and Microsoft reveals that the utilization of production GPU clusters in the industry is generally between 25% and 50%. This indicates a significant opportunity for improvement. To this end, AI accelerator resource sharing has emerged as a promising approach to the performance optimization of multi-tenant clusters. This survey covers this line of studies from 2016 to 2024, focusing primarily on system efficiency while also including discussion on fairness, interference, and security in AI accelerator sharing. We revisit the fundamentals and key concepts, followed by a comprehensive review of recent advances in the field. We find that over 70% of the studies focus on efficiency improvement. We also observe that approximately half of the reviewed studies have made their source code publicly available, while fewer than one-third of the studies did not utilize a physical machine for experimentation. Finally, based on the limitations of existing research, we outline several directions for future research concerning the integration of sharing with large language models (LLMs), coordination between schedulers and application-layer metrics, and collaboration among heterogeneous accelerators.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"9 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143538376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Evangelia Konstantopoulou, George Athanasiou, Nicolas Sklavos
The National Institute of Standards and Technology (NIST) initiated the lightweight cryptography (LWC) competition to facilitate Internet of Things (IoT) application security. This review explores hardware implementations of the NIST LWC finalists, studying their performance. A detailed comparison of FPGA and ASIC implementations is provided, summarizing both straightforward and optimized designs. It serves as a valuable resource for engineers and researchers, aiding in the selection of algorithms tailored to specific IoT application requirements. ASCON emerges as the most balanced performer, offering excellent throughput, area efficiency, and security. Meanwhile, TinyJAMBU and Grain128-AEAD excel in constrained environments and low-latency use cases.
{"title":"Review and Analysis of FPGA and ASIC Implementations of NIST Lightweight Cryptography Finalists","authors":"Evangelia Konstantopoulou, George Athanasiou, Nicolas Sklavos","doi":"10.1145/3721122","DOIUrl":"https://doi.org/10.1145/3721122","url":null,"abstract":"The National Institute of Standards and Technology (NIST) initiated the lightweight cryptography (LWC) competition to facilitate Internet of Things (IoT) application security. This review explores hardware implementations of the NIST LWC finalists, studying their performance. A detailed comparison of FPGA and ASIC implementations is provided, summarizing both straightforward and optimized designs. It serves as a valuable resource for engineers and researchers, aiding in the selection of algorithms tailored to specific IoT application requirements. ASCON emerges as the most balanced performer, offering excellent throughput, area efficiency, and security. Meanwhile, TinyJAMBU and Grain128-AEAD excel in constrained environments and low-latency use cases.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"529 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143526212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Li Li, Xiang Gao, Hailong Sun, Chunming Hu, Xiaoyu Sun, Haoyu Wang, Haipeng Cai, Ting Su, Xiapu Luo, Tegawendé Bissyande, Jacques Klein, John Grundy, Tao Xie, Haibo Chen, Huaimin Wang
Mobile software engineering has been a hot research topic for decades. Our fellow researchers have proposed various approaches (with over 7,000 publications for Android alone) in this field that essentially contributed to the great success of the current mobile ecosystem. Existing research efforts mainly focus on popular mobile platforms, namely Android and iOS. OpenHarmony, a newly open-sourced mobile platform, has rarely been considered, although it is the one requiring the most attention as OpenHarmony is expected to occupy one-third of the market in China (if not in the world). To fill the gap, we present to the mobile software engineering community a research roadmap for encouraging our fellow researchers to contribute promising approaches to OpenHarmony. Specifically, we start by presenting a tertiary study of mobile software engineering, attempting to understand what problems have been targeted by the mobile community and how they have been resolved. We then summarize the existing (limited) achievements of OpenHarmony and subsequently highlight the research gap between Android/iOS and OpenHarmony. This research gap eventually helps in forming the roadmap for conducting software engineering research for OpenHarmony.
{"title":"Software Engineering for OpenHarmony: A Research Roadmap","authors":"Li Li, Xiang Gao, Hailong Sun, Chunming Hu, Xiaoyu Sun, Haoyu Wang, Haipeng Cai, Ting Su, Xiapu Luo, Tegawendé Bissyande, Jacques Klein, John Grundy, Tao Xie, Haibo Chen, Huaimin Wang","doi":"10.1145/3720538","DOIUrl":"https://doi.org/10.1145/3720538","url":null,"abstract":"Mobile software engineering has been a hot research topic for decades. Our fellow researchers have proposed various approaches (with over 7,000 publications for Android alone) in this field that essentially contributed to the great success of the current mobile ecosystem. Existing research efforts mainly focus on popular mobile platforms, namely Android and iOS. OpenHarmony, a newly open-sourced mobile platform, has rarely been considered, although it is the one requiring the most attention as OpenHarmony is expected to occupy one-third of the market in China (if not in the world). To fill the gap, we present to the mobile software engineering community a research roadmap for encouraging our fellow researchers to contribute promising approaches to OpenHarmony. Specifically, we start by presenting a tertiary study of mobile software engineering, attempting to understand what problems have been targeted by the mobile community and how they have been resolved. We then summarize the existing (limited) achievements of OpenHarmony and subsequently highlight the research gap between Android/iOS and OpenHarmony. This research gap eventually helps in forming the roadmap for conducting software engineering research for OpenHarmony.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"187 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143507102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhuosheng Zhang, Yao Yao, Aston Zhang, Xiangru Tang, Xinbei Ma, Zhiwei He, Yiming Wang, Mark Gerstein, Rui Wang, Gongshen Liu, Hai Zhao
Large language models (LLMs) have dramatically enhanced the field of language intelligence, as demonstrably evidenced by their formidable empirical performance across a spectrum of complex reasoning tasks. Additionally, theoretical proofs have illuminated their emergent reasoning capabilities, providing a compelling showcase of their advanced cognitive abilities in linguistic contexts. Critical to their remarkable efficacy in handling complex reasoning tasks, LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. The CoT reasoning approach has not only exhibited proficiency in amplifying reasoning performance but also in enhancing interpretability, controllability, and flexibility. In light of these merits, recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents, which adeptly adhere to language instructions and execute actions within varied environments. This survey paper orchestrates a thorough discourse, penetrating vital research dimensions, encompassing: (i) the foundational mechanics of CoT techniques, with a focus on elucidating the circumstances and justification behind its efficacy; (ii) the paradigm shift in CoT; and (iii) the burgeoning of language agents fortified by CoT approaches. Prospective research avenues envelop explorations into generalization, efficiency, customization, scaling, and safety. A repository for the related papers is available at https://github.com/Zoeyyao27/CoT-Igniting-Agent.
{"title":"Igniting Language Intelligence: The Hitchhiker's Guide from Chain-of-Thought Reasoning to Language Agents","authors":"Zhuosheng Zhang, Yao Yao, Aston Zhang, Xiangru Tang, Xinbei Ma, Zhiwei He, Yiming Wang, Mark Gerstein, Rui Wang, Gongshen Liu, Hai Zhao","doi":"10.1145/3719341","DOIUrl":"https://doi.org/10.1145/3719341","url":null,"abstract":"Large language models (LLMs) have dramatically enhanced the field of language intelligence, as demonstrably evidenced by their formidable empirical performance across a spectrum of complex reasoning tasks. Additionally, theoretical proofs have illuminated their emergent reasoning capabilities, providing a compelling showcase of their advanced cognitive abilities in linguistic contexts. Critical to their remarkable efficacy in handling complex reasoning tasks, LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. The CoT reasoning approach has not only exhibited proficiency in amplifying reasoning performance but also in enhancing interpretability, controllability, and flexibility. In light of these merits, recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents, which adeptly adhere to language instructions and execute actions within varied environments. This survey paper orchestrates a thorough discourse, penetrating vital research dimensions, encompassing: (i) the foundational mechanics of CoT techniques, with a focus on elucidating the circumstances and justification behind its efficacy; (ii) the paradigm shift in CoT; and (iii) the burgeoning of language agents fortified by CoT approaches. Prospective research avenues envelop explorations into generalization, efficiency, customization, scaling, and safety. A repository for the related papers is available at https://github.com/Zoeyyao27/CoT-Igniting-Agent.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"31 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143495336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：