Cong Feng

Junjie Huang, Zhihan Jiang, Jinyang Liu et al.

Logs are imperative in the maintenance of online service systems, which often encompass important information for effective failure mitigation. While existing anomaly detection methodologies facilitate the identification of anomalous logs within extensive runtime data, manual investigation of log messages by engineers remains essential to comprehend faults, which is labor-intensive and error-prone. Upon examining the log-based troubleshooting practices at CloudA, we find that engineers typically prioritize two categories of log information for diagnosis. These include fault-indicating descriptions, which record abnormal system events, and fault-indicating parameters, which specify the associated entities. Motivated by this finding, we propose an approach to automatically extract such faultindicating information from logs for fault diagnosis, named LoFI. LoFI comprises two key stages. In the first stage, LoFI performs coarse-grained filtering to collect logs related to the faults based on semantic similarity. In the second stage, LoFI leverages a pre-trained language model with a novel prompt-based tuning method to extract fine-grained information of interest from the collected logs. We evaluate LoFI on logs collected from Apache Spark and an industrial dataset from CloudA. The experimental results demonstrate that LoFI outperforms all baseline methods by a significant margin, achieving an absolute improvement of 25.8~37.9 in F1 over the best baseline method, ChatGPT. This highlights the effectiveness of LoFI in recognizing fault-indicating information. Furthermore, the successful deployment of LoFI at CloudA and user studies validate the utility of our method. The code and data are available at https://github.com/Jun-jie-Huang/LoFI.

Yingfa Chen, Chenlong Hu, Cong Feng et al. · tsinghua

This study presents a multi-modal multi-granularity tokenizer specifically designed for analyzing ancient Chinese scripts, focusing on the Chu bamboo slip (CBS) script used during the Spring and Autumn and Warring States period (771-256 BCE) in Ancient China. Considering the complex hierarchical structure of ancient Chinese scripts, where a single character may be a combination of multiple sub-characters, our tokenizer first adopts character detection to locate character boundaries, and then conducts character recognition at both the character and sub-character levels. Moreover, to support the academic community, we have also assembled the first large-scale dataset of CBSs with over 100K annotated character image scans. On the part-of-speech tagging task built on our dataset, using our tokenizer gives a 5.5% relative improvement in F1-score compared to mainstream sub-word tokenizers. Our work not only aids in further investigations of the specific script but also has the potential to advance research on other forms of ancient Chinese scripts.

Jinyang Liu, Tianyi Yang, Zhuangbin Chen et al.

As modern software systems continue to grow in terms of complexity and volume, anomaly detection on multivariate monitoring metrics, which profile systems' health status, becomes more and more critical and challenging. In particular, the dependency between different metrics and their historical patterns plays a critical role in pursuing prompt and accurate anomaly detection. Existing approaches fall short of industrial needs for being unable to capture such information efficiently. To fill this significant gap, in this paper, we propose CMAnomaly, an anomaly detection framework on multivariate monitoring metrics based on collaborative machine. The proposed collaborative machine is a mechanism to capture the pairwise interactions along with feature and temporal dimensions with linear time complexity. Cost-effective models can then be employed to leverage both the dependency between monitoring metrics and their historical patterns for anomaly detection. The proposed framework is extensively evaluated with both public data and industrial data collected from a large-scale online service system of Huawei Cloud. The experimental results demonstrate that compared with state-of-the-art baseline models, CMAnomaly achieves an average F1 score of 0.9494, outperforming baselines by 6.77% to 10.68%, and runs 10X to 20X faster. Furthermore, we also share our experience of deploying CMAnomaly in Huawei Cloud.

Wenwei Gu, Jinyang Liu, Zhuangbin Chen et al.

Cloud systems are susceptible to performance issues, which may cause service-level agreement violations and financial losses. In current practice, crucial metrics are monitored periodically to provide insight into the operational status of components. Identifying performance issues is often formulated as an anomaly detection problem, which is tackled by analyzing each metric independently. However, this approach overlooks the complex dependencies existing among cloud components. Some graph neural network-based methods take both temporal and relational information into account, however, the correlation violations in the metrics that serve as indicators of underlying performance issues are difficult for them to identify. Furthermore, a large volume of components in a cloud system results in a vast array of noisy metrics. This complexity renders it impractical for engineers to fully comprehend the correlations, making it challenging to identify performance issues accurately. To address these limitations, we propose Identifying Performance Issues based on Relational-Temporal Features (ISOLATE ), a learning-based approach that leverages both the relational and temporal features of metrics to identify performance issues. In particular, it adopts a graph neural network with attention to characterizing the relations among metrics and extracts long-term and multi-scale temporal patterns using a GRU and a convolution network, respectively. The learned graph attention weights can be further used to localize the correlation-violated metrics. Moreover, to relieve the impact of noisy data, ISOLATE utilizes a positive unlabeled learning strategy that tags pseudo-labels based on a small portion of confirmed negative examples. Extensive evaluation on both public and industrial datasets shows that ISOLATE outperforms all baseline models with 0.945 F1-score and 0.920 Hit rate@3.

Mengyin Lu, Cong Feng, Huimin Han et al.

Automatic prompt engineering (APE) rewrites prompts to improve downstream task performance, but existing APE loops treat the optimizer itself as a fixed pipeline. We port the code-as-action paradigm of CodeAct (Wang et al., 2024a) to APE and propose SPEAR (Sandboxed Prompt Engineer with Active Roll-back), a free-form agentic optimizer with four tools -- evaluate, python, set_prompt, finish -- that decides autonomously how and when to use them. The distinctive tool is the Python sandbox: the optimizer writes and executes arbitrary Python on the current evaluation DataFrame, performing structural error analysis (confusion matrices, error clustering, per group metrics) the agent itself authors. Two guardrails turn the long-horizon agent into a monotone-improving optimizer: auto-rollback on metric regression, and an optional guard metric floor. We evaluate on three industrial LLM-as-judge suites (13 judge tasks across recruiter-intake, conversational-memory, and query-refinement systems) plus seven BBH tasks and GSM8K. SPEAR wins every industrial task on the primary metric ($κ$ 0.857 vs 0.359 on tool-selection; F1-macro 0.815 vs 0.763 on filter-relevance; $κ$ 0.254 vs 0.218 on the hardest extraction dimension). On BBH-7 SPEAR averages 0.938 accuracy vs GEPA 0.628 and TextGrad 0.484. Ablations show the Python tool is the largest single lever on complex judge tasks ($Δ\approx +0.79κ$ on the 5-class tool-selection judge, $Δ\approx +0.35κ$ on the hardest extraction dimension when removed); its irreplaceable contribution is class-pair confusion aggregation that a long-context LLM cannot extract reliably from the raw eval DataFrame.

Jinyang Liu, Junjie Huang, Yintong Huo et al.

System logs play a critical role in maintaining the reliability of software systems. Fruitful studies have explored automatic log-based anomaly detection and achieved notable accuracy on benchmark datasets. However, when applied to large-scale cloud systems, these solutions face limitations due to high resource consumption and lack of adaptability to evolving logs. In this paper, we present an accurate, lightweight, and adaptive log-based anomaly detection framework, referred to as SeaLog. Our method introduces a Trie-based Detection Agent (TDA) that employs a lightweight, dynamically-growing trie structure for real-time anomaly detection. To enhance TDA's accuracy in response to evolving log data, we enable it to receive feedback from experts. Interestingly, our findings suggest that contemporary large language models, such as ChatGPT, can provide feedback with a level of consistency comparable to human experts, which can potentially reduce manual verification efforts. We extensively evaluate SeaLog on two public datasets and an industrial dataset. The results show that SeaLog outperforms all baseline methods in terms of effectiveness, runs 2X to 10X faster and only consumes 5% to 41% of the memory resource.

Ruiyang Ren, Yuhao Wang, Yunsen Liang et al.

Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems are misaligned with this reality, treating diagnosis as single-pass retrospective prediction while lacking auditable mechanisms for governed improvement. We developed DxEvolve, a self-evolving diagnostic agent that bridges these gaps through an interactive deep clinical research workflow. The framework autonomously requisitions examinations and continually externalizes clinical experience from increasing encounter exposure as diagnostic cognition primitives. On the MIMIC-CDM benchmark, DxEvolve improved diagnostic accuracy by 11.2% on average over backbone models and reached 90.4% on a reader-study subset, comparable to the clinician reference (88.8%). DxEvolve improved accuracy on an independent external cohort by 10.2% (categories covered by the source cohort) and 17.1% (uncovered categories) compared to the competitive method. By transforming experience into a governable learning asset, DxEvolve supports an accountable pathway for the continual evolution of clinical AI.

Junjie Huang, Jinyang Liu, Zhuangbin Chen et al.

Postmortem analysis is essential in the management of incidents within cloud systems, which provides valuable insights to improve system's reliability and robustness. At CloudA, fault pattern profiling is performed during the postmortem phase, which involves the classification of incidents' faults into unique categories, referred to as fault pattern. By aggregating and analyzing these fault patterns, engineers can discern common faults, vulnerable components and emerging fault trends. However, this process is currently conducted by manual labeling, which has inherent drawbacks. On the one hand, the sheer volume of incidents means only the most severe ones are analyzed, causing a skewed overview of fault patterns. On the other hand, the complexity of the task demands extensive domain knowledge, which leads to errors and inconsistencies. To address these limitations, we propose an automated approach, named FaultProfIT, for Fault pattern Profiling of Incident Tickets. It leverages hierarchy-guided contrastive learning to train a hierarchy-aware incident encoder and predicts fault patterns with enhanced incident representations. We evaluate FaultProfIT using the production incidents from CloudA. The results demonstrate that FaultProfIT outperforms state-of-the-art methods. Our ablation study and analysis also verify the effectiveness of hierarchy-guided contrastive learning. Additionally, we have deployed FaultProfIT at CloudA for six months. To date, FaultProfIT has analyzed 10,000+ incidents from 30+ cloud services, successfully revealing several fault trends that have informed system improvements.

Ziheng Wang, Cong Feng, Jie Zhang et al.

Providing an accurate and efficient assessment of operative difficulty is important for designing robot-assisted teleoperation interfaces that are easy and natural for human operators to use. In this paper, we aim to develop a data-driven approach to numerically characterize the operative difficulty demand of complex teleoperation. In effort to provide an entirely task-independent assessment, we consider using only data collected from the human user including: (1) physiological response, and (2) movement kinematics. By leveraging an unsupervised domain adaptation technique, our approach learns the user information that defines task difficulty in a well-known source, namely, a Fitt's target reaching task, and generalizes that knowledge to a more complex human motor control scenario, namely, the teleoperation of a robotic system. Our approach consists of two main parts: (1) The first part accounts for the inherent variances of user physiological and kinematic response between these cross-domain motor control scenarios that are vastly different. (2) A stacked two-layer learner is designed to improve the overall modeling performance, yielding a 96.6% accuracy in predicting the known difficulty of a Fitts' reaching task when using movement kinematic features. We then validate the effectiveness of our model by investigating teleoperated robotic needle steering as a case study. Compared with a standard NASA TLX user survey, our results indicate significant differences in the difficulty demand for various choices of needle steering control algorithms, p<0.05, as well as the difficulty of steering the needle to different targets, p<0.05. The results highlight the potential of our approach to be used as a design tool to create more intuitive and natural teleoperation interfaces in robot-assisted systems.

Cong Feng, Jie Zhang

With the growing prevalence of smart grid technology, short-term load forecasting (STLF) becomes particularly important in power system operations. There is a large collection of methods developed for STLF, but selecting a suitable method under varying conditions is still challenging. This paper develops a novel reinforcement learning based dynamic model selection (DMS) method for STLF. A forecasting model pool is first built, including ten state-of-the-art machine learning based forecasting models. Then a Q-learning agent learns the optimal policy of selecting the best forecasting model for the next time step, based on the model performance. The optimal DMS policy is applied to select the best model at each time step with a moving window. Numerical simulations on two-year load and weather data show that the Q-learning algorithm converges fast, resulting in effective and efficient DMS. The developed STLF model with Q-learning based DMS improves the forecasting accuracy by approximately 50%, compared to the state-of-the-art machine learning based STLF models.

Cong Feng, Mingjian Cui, Bri-Mathias Hodge et al.

Solar forecasting accuracy is affected by weather conditions, and weather awareness forecasting models are expected to improve the performance. However, it may not be available and reliable to classify different forecasting tasks by using only meteorological weather categorization. In this paper, an unsupervised clustering-based (UC-based) solar forecasting methodology is developed for short-term (1-hour-ahead) global horizontal irradiance (GHI) forecasting. This methodology consists of three parts: GHI time series unsupervised clustering, pattern recognition, and UC-based forecasting. The daily GHI time series is first clustered by an Optimized Cross-validated ClUsteRing (OCCUR) method, which determines the optimal number of clusters and best clustering results. Then, support vector machine pattern recognition (SVM-PR) is adopted to recognize the category of a certain day using the first few hours' data in the forecasting stage. GHI forecasts are generated by the most suitable models in different clusters, which are built by a two-layer Machine learning based Multi-Model (M3) forecasting framework. The developed UC-based methodology is validated by using 1-year of data with six solar features. Numerical results show that (i) UC-based models outperform non-UC (all-in-one) models with the same M3 architecture by approximately 20%; (ii) M3-based models also outperform the single-algorithm machine learning (SAML) models by approximately 20%.

Cong Feng, Jie Zhang

With the increasing penetration of solar power into power systems, forecasting becomes critical in power system operations. In this paper, an hourly-similarity (HS) based method is developed for 1-hour-ahead (1HA) global horizontal irradiance (GHI) forecasting. This developed method utilizes diurnal patterns, statistical distinctions between different hours, and hourly similarities in solar data to improve the forecasting accuracy. The HS-based method is built by training multiple two-layer multi-model forecasting framework (MMFF) models independently with the same-hour subsets. The final optimal model is a combination of MMFF models with the best-performed blending algorithm at every hour. At the forecasting stage, the most suitable model is selected to perform the forecasting subtask of a certain hour. The HS-based method is validated by 1-year data with six solar features collected by the National Renewable Energy Laboratory (NREL). Results show that the HS-based method outperforms the non-HS (all-in-one) method significantly with the same MMFF architecture, wherein the optimal HS- based method outperforms the best all-in-one method by 10.94% and 7.74% based on the normalized mean absolute error and normalized root mean square error, respectively.