LLM Agents for Time-Series: A Survey
本文通过问题驱动的分类方法，总结了基于大语言模型的时间序列处理系统，并探讨了任务需求如何影响代理设计，为未来研究指明方向。
0 citationsRead paper
Selected work
Representative Papers
Evaluating for the long term: Learnings from industry
Short-term online experiments often fail to accurately predict long-term business outcomes, potentially leading to decisions misaligned with strategic objectives. Drawing on insights from industry expert workshops, this work proposes a design principle for surrogate metrics centered on decision utility rather than solely on unbiasedness, advocating that interpretable, experiment-driven simple surrogates outperform complex black-box models. Through expert consensus synthesis, surrogate metric analysis, and comparative evaluation of experimental versus observational data, the study systematically outlines a methodology for constructing effective surrogates and uncovers a critical relationship between the stability of long-term effects and surrogate validity. While underscoring the irreplaceable value of high-quality long-term experimentation, the research also delineates core challenges and practical guidelines for surrogate learning in real-world settings.
0 citationsRead paper
Post-Training in Time Series Foundation Models: A Unifying Framework
Pretrained time series foundation models often underperform on downstream tasks due to domain shift, task heterogeneity, scarce labeled data, and computational constraints. This work proposes the first systematic post-training framework, categorizing existing approaches along five dimensions based on their intervention points within the forecasting pipeline: parameter adaptation, context augmentation, model composition, output and uncertainty calibration, and compression with specialization. By delineating the design space and inherent limitations of each category, the framework offers a structured pathway to bridge the gap between pretraining and reliable deployment, thereby advancing the standardization and systematic development of time series post-training methodologies.
0 citationsRead paper
Kani: A Model Checker for Rust
This work addresses the limitations of Rust’s compiler in guaranteeing memory safety, functional correctness, and panic freedom for unsafe code. The authors present the first open-source verification framework for Rust that integrates both bounded and unbounded model checking. By precisely translating Rust’s Mid-level Intermediate Representation (MIR) into input suitable for the C Bounded Model Checker (CBMC), and by incorporating function and loop contracts, quantifiers, and stub functions, the framework enables fully automated verification without requiring user annotations. Evaluated on industrial-scale codebases, the approach uncovered six previously unknown vulnerabilities and has been integrated into the Rust standard library’s continuous integration pipeline, where it automatically verifies over 16,000 verification harnesses with every code change.
0 citationsRead paper
ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues
This work addresses the limitations of existing reproducibility assessment methods, which rely on manual annotations and thus lack scalability and authentic supervision signals reflecting real-world reproduction challenges. The authors propose the first scalable evaluation framework that leverages GitHub user-submitted issues as natural supervision, enabling large-scale assessment of large language model (LLM) agents’ ability to identify paper-to-code reproducibility issues without human annotation. By integrating language understanding with code context analysis, the approach enables non-execution-based detection of reproducibility barriers. Experimental results demonstrate that the best-performing LLM agent identifies at least one semantically relevant reproducibility issue—aligned with those reported by humans—in approximately 90% of the evaluated papers, exhibiting strong performance in both failure detection and semantic localization.
0 citationsRead paper
Recent publications
Latest Papers
LLM Agents for Time-Series: A Survey
本文通过问题驱动的分类方法，总结了基于大语言模型的时间序列处理系统，并探讨了任务需求如何影响代理设计，为未来研究指明方向。
0 citationsRead paper
Evaluating for the long term: Learnings from industry
Short-term online experiments often fail to accurately predict long-term business outcomes, potentially leading to decisions misaligned with strategic objectives. Drawing on insights from industry expert workshops, this work proposes a design principle for surrogate metrics centered on decision utility rather than solely on unbiasedness, advocating that interpretable, experiment-driven simple surrogates outperform complex black-box models. Through expert consensus synthesis, surrogate metric analysis, and comparative evaluation of experimental versus observational data, the study systematically outlines a methodology for constructing effective surrogates and uncovers a critical relationship between the stability of long-term effects and surrogate validity. While underscoring the irreplaceable value of high-quality long-term experimentation, the research also delineates core challenges and practical guidelines for surrogate learning in real-world settings.
0 citationsRead paper
Post-Training in Time Series Foundation Models: A Unifying Framework
Pretrained time series foundation models often underperform on downstream tasks due to domain shift, task heterogeneity, scarce labeled data, and computational constraints. This work proposes the first systematic post-training framework, categorizing existing approaches along five dimensions based on their intervention points within the forecasting pipeline: parameter adaptation, context augmentation, model composition, output and uncertainty calibration, and compression with specialization. By delineating the design space and inherent limitations of each category, the framework offers a structured pathway to bridge the gap between pretraining and reliable deployment, thereby advancing the standardization and systematic development of time series post-training methodologies.
0 citationsRead paper
Kani: A Model Checker for Rust
This work addresses the limitations of Rust’s compiler in guaranteeing memory safety, functional correctness, and panic freedom for unsafe code. The authors present the first open-source verification framework for Rust that integrates both bounded and unbounded model checking. By precisely translating Rust’s Mid-level Intermediate Representation (MIR) into input suitable for the C Bounded Model Checker (CBMC), and by incorporating function and loop contracts, quantifiers, and stub functions, the framework enables fully automated verification without requiring user annotations. Evaluated on industrial-scale codebases, the approach uncovered six previously unknown vulnerabilities and has been integrated into the Rust standard library’s continuous integration pipeline, where it automatically verifies over 16,000 verification harnesses with every code change.
0 citationsRead paper
ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues
This work addresses the limitations of existing reproducibility assessment methods, which rely on manual annotations and thus lack scalability and authentic supervision signals reflecting real-world reproduction challenges. The authors propose the first scalable evaluation framework that leverages GitHub user-submitted issues as natural supervision, enabling large-scale assessment of large language model (LLM) agents’ ability to identify paper-to-code reproducibility issues without human annotation. By integrating language understanding with code context analysis, the approach enables non-execution-based detection of reproducibility barriers. Experimental results demonstrate that the best-performing LLM agent identifies at least one semantically relevant reproducibility issue—aligned with those reported by humans—in approximately 90% of the evaluated papers, exhibiting strong performance in both failure detection and semantic localization.
0 citationsRead paper