While agentic AI systems rely on LLMs to translate user intent into structured function calls, this process is fraught with computational redundancy, leading to high inference latency that hinders real-time applications. This paper identifies and addresses three key redundancies: (1) the redundant processing of a large library of function descriptions for every request; (2) the redundant use of a large, slow model to generate an entire, often predictable, token sequence; and (3) the redundant generation of fixed, boilerplate parameter syntax. We introduce HyFunc, a novel framework that systematically eliminates these inefficiencies. HyFunc employs a hybrid-model cascade where a large model distills user intent into a single ''soft token.'' This token guides a lightweight retriever to select relevant functions and directs a smaller, prefix-tuned model to generate the final call, thus avoiding redundant context processing and full-sequence generation by the large model. To eliminate syntactic redundancy, our ''dynamic templating'' technique injects boilerplate parameter syntax on-the-fly within an extended vLLM engine. To avoid potential limitations in generalization, we evaluate HyFunc on an unseen benchmark dataset, BFCL. Experimental results demonstrate that HyFunc achieves an excellent balance between efficiency and performance. It achieves an inference latency of 0.828 seconds, outperforming all baseline models, and reaches a performance of 80.1%, surpassing all models with a comparable parameter scale. These results suggest that HyFunc offers a more efficient paradigm for agentic AI. Our code is publicly available at https://github.com/MrBlankness/HyFunc.

This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings. Using a PRISMA-inspired framework, we systematically reviewed nearly 250 scholarly sources, capturing the state-of-the-art from various venues of publication, and establishing a solid foundation for our analysis. Our study offers a structured approach by developing two interrelated taxonomy systems: one that defines what to evaluate and another that explains how to evaluate . The first taxonomy identifies key components of LLM-based agents for multi-turn conversations and their evaluation dimensions, including task completion, response quality, user experience, memory and context retention, as well as planning and tool integration. These components ensure that the performance of conversational agents is assessed in a holistic and meaningful manner. The second taxonomy system focuses on the evaluation methodologies. It categorizes approaches into annotation-based evaluations, automated metrics, hybrid strategies that combine human assessments with quantitative measures, and self-judging methods utilizing LLMs. This framework not only captures traditional metrics derived from language understanding, such as BLEU and ROUGE scores, but also incorporates advanced techniques that reflect the dynamic, interactive nature of multi-turn dialogues. Together, these frameworks summarize the current status quo, expose limitations in traditional practices, and provide a structured blueprint for improvement. Based on the summarization of existing studies, we identify several challenges and propose future directions, including the development of scalable, real-time evaluation pipelines, enhanced privacy-preserving mechanisms, and robust metrics that capture dynamic multi-turn interactions. Our contributions bridge historical insights with modern practices, paving the way for next-generation, reliably evaluated conversational AI systems and offering a comprehensive guide for researchers and practitioners.

Recent years, Pre-trained Language models (PLMs) have swept into various fields of artificial intelligence and achieved great success. However, most PLMs, such as T5 and GPT3, have a huge amount of parameters, fine-tuning them is often expensive and time consuming, and storing them takes up a lot of space. Therefore, it is necessary to adopt a parameter-efficient approach to reduce parameters of PLMs in fine-tuning without compromising their performance in downstream tasks. In this paper, we design a novel adapter which only acts on self-attention outputs in PLMs. This adapter adopts element-wise linear transformation using Hadamard product, hence named as Hadamard adapter, requires the fewest parameters compared to previous parameter-efficient adapters. In addition, we also summarize some tuning patterns for Hadamard adapter shared by various downstream tasks, expecting to provide some guidance for further parameter reduction with shared adapters in future studies. The experiments conducted on the widely-used GLUE benchmark with several SOTA PLMs prove that the Hadamard adapter achieves competitive performance with only 0.033% parameters compared with full fine-tuning, and it has the fewest parameters compared with other adapters. Moreover, we further find that there is also some redundant layers in the Hadamard adapter which can be removed to achieve more parameter efficiency with only 0.022% parameters.

Modern search engines retrieve results mainly based on the keyword matching techniques, and thus fail to answer analytical queries like "apps with more than 1 billion monthly active users" or "population growth of the US from 2015 to 2019", which requires numerical reasoning or aggregating results from multiple web pages. Such analytical queries are very common in the data analysis area, the expected results would be structured tables or charts. In most cases, these structured results are not available or accessible, they scatter in various text sources. In this work, we build AnaSearch, a search system to support analytical queries, and return structured results that can be visualized in the form of tables or charts. We collect and build structured quantitative data from the unstructured text on the web automatically. With AnaSearch, data analysts could easily derive insights for decision making with keyword or natural language queries. Specifically, we build AnaSearch under the COVID-19 news data, which makes it easy to compare with manually collected structured data.

Recommendation models mainly deal with categorical variables, such as user/item ID and attributes. Besides the high-cardinality issue, the interactions among such categorical variables are usually long-tailed, with the head made up of highly frequent values and a long tail of rare ones. This phenomenon results in the data sparsity issue, making it essential to regularize the models to ensure generalization. The common practice is to employ grid search to manually tune regularization hyperparameters based on the validation data. However, it requires non-trivial efforts and large computation resources to search the whole candidate space; even so, it may not lead to the optimal choice, for which different parameters should have different regularization strengths. In this paper, we propose a hyperparameter optimization method, lambdaOpt, which automatically and adaptively enforces regularization during training. Specifically, it updates the regularization coefficients based on the performance of validation data. With lambdaOpt, the notorious tuning of regularization hyperparameters can be avoided; more importantly, it allows fine-grained regularization (i.e. each parameter can have an individualized regularization coefficient), leading to better generalized models. We show how to employ lambdaOpt on matrix factorization, a classical model that is representative of a large family of recommender models. Extensive experiments on two public benchmarks demonstrate the superiority of our method in boosting the performance of top-K recommendation.

Almost all the knowledge empowered applications rely upon accurate knowledge, which has to be either collected manually with high cost, or extracted automatically with unignorable errors. In this paper, we study 20 Questions, an online interactive game where each question-response pair corresponds to a fact of the target entity, to acquire highly accurate knowledge effectively with nearly zero labor cost. Knowledge acquisition via 20 Questions predominantly presents two challenges to the intelligent agent playing games with human players. The first one is to seek enough information and identify the target entity with as few questions as possible, while the second one is to leverage the remaining questioning opportunities to acquire valuable knowledge effectively, both of which count on good questioning strategies. To address these challenges, we propose the Learning-to-Ask (LA) framework, within which the agent learns smart questioning strategies for information seeking and knowledge acquisition by means of deep reinforcement learning and generalized matrix factorization respectively. In addition, a Bayesian approach to represent knowledge is adopted to ensure robustness to noisy user responses. Simulating experiments on real data show that LA is able to equip the agent with effective questioning strategies, which result in high winning rates and rapid knowledge acquisition. Moreover, the questioning strategies for information seeking and knowledge acquisition boost the performance of each other, allowing the agent to start with a relatively small knowledge set and quickly improve its knowledge base in the absence of constant human supervision.

The ability to identify insights from multi-dimensional big data is important for business intelligence. To enable interactive identification of insights, a large number of dimension combinations need to be searched and a series of aggregation queries need to be quickly answered. The existing approaches answer interactive queries on big data through data cubes or approximate query processing. However, these approaches can hardly satisfy the performance or accuracy requirements for ad-hoc queries demanded by interactive exploration. In this paper, we present BigIN4, a system for instant, interactive identification of insights from multi-dimensional big data. BigIN4 gives insight suggestions by enumerating subspaces and answers queries by combining data cube and approximate query processing techniques. If a query cannot be answered by the cubes, BigIN4 decomposes it into several low dimensional queries that can be directly answered by the cubes through an online constructed Bayesian Network and gives an approximate answer within a statistical interval. Unlike the related works, BigIN4 does not require any prior knowledge of queries and does not assume a certain data distribution. Our experiments on ten real-world large-scale datasets show that BigIN4 can successfully identify insights from big data. Furthermore, BigIN4 can provide approximate answers to aggregation queries effectively (with less than 10% error on average) and efficiently (50x faster than sampling-based methods).

For a large-scale software system, especially an online service system, when a performance issue occurs, it is desirable to check whether this issue has occurred before. If there are past similar issues, a known remedy could be applied. Otherwise, a new troubleshooting process may have to be initiated. The symptom of a performance issue can be characterized by a set of metrics. Due to the sophisticated nature of software systems, manual diagnosis of performance issues based on metric data is typically expensive and laborious. In this paper, we propose a Hidden Markov Random Field (HMRF) based approach to automatic identification of recurrent and unknown performance issues. We formulate the problem of issue identification as a HMRF-based clustering problem. Our approach incorporates the learning of metric discretization thresholds and the optimization of issue clustering. Based on the learned thresholds and cluster centroids, we can achieve accurate identification of recurrent issues and unknown issues. Experimental evaluations on an open benchmark and a large-scale industrial production system show that our approach is effective and outperforms the related state-of-the-art approaches.

As online services have more and more popular, incident diagnosis has emerged as a critical task in minimizing the service downtime and ensuring high quality of the services provided. For most online services, incident diagnosis is mainly conducted by analyzing a large amount of telemetry data collected from the services at runtime. Time series data and event sequence data are two major types of telemetry data. Techniques of correlation analysis are important tools that are widely used by engineers for data-driven incident diagnosis. Despite their importance, there has been little previous work addressing the correlation between two types of heterogeneous data for incident diagnosis: continuous time series data and temporal event data. In this paper, we propose an approach to evaluate the correlation between time series data and event data. Our approach is capable of discovering three important aspects of event-timeseries correlation in the context of incident diagnosis: existence of correlation, temporal order, and monotonic effect. Our experimental results on simulation data sets and two real data sets demonstrate the effectiveness of the algorithm.

Understanding the behaviors of a software system is very important for performing daily system maintenance tasks. In practice, one way to gain knowledge about the runtime behavior of a system is to manually analyze system logs collected during the system executions. With the increasing scale and complexity of software systems, it has become challenging for system operators to manually analyze system logs. To address these challenges, in this paper, we propose a new approach for contextual analysis of system logs for understanding a system's behaviors. In particular, we first use execution patterns to represent execution structures reflected by a sequence of system logs, and propose an algorithm to mine execution patterns from the program logs. The mined execution patterns correspond to different execution paths of the system. Based on these execution patterns, our approach further learns essential contextual factors (e.g., the occurrences of specific program logs with specific parameter values) that cause a specific branch or path to be executed by the system. The mining and learning results can help system operators to understand a software system's runtime execution logic and behaviors during various tasks such as system problem diagnosis. We demonstrate the feasibility of our approach upon two real-world software systems (Hadoop and Ethereal).

Successful software maintenance is becoming increasingly critical due to the increasing dependence of our society and economy on software systems. One key problem of software maintenance is the difficulty in understanding the evolving software systems. Program workflows can help system operators and administrators to understand system behaviors and verify system executions so as to greatly facilitate system maintenance. In this paper, we propose an algorithm to automatically discover program workflows from event traces that record system events during system execution. Different from existing workflow mining algorithms, our approach can construct concurrent workflows from traces of interleaved events. Our workflow mining approach is a three-step coarse-to-fine algorithm. At first, we mine temporal dependencies for each pair of events. Then, based on the mined pair-wise tem-poral dependencies, we construct a basic workflow model by a breadth-first path pruning algorithm. After that, we refine the workflow by verifying it with all training event traces. The re-finement algorithm tries to find out a workflow that can interpret all event traces with minimal state transitions and threads. The results of both simulation data and real program data show that our algorithm is highly effective.

Detection of execution anomalies is very important for the maintenance, development, and performance refinement of large scale distributed systems. Execution anomalies include both work flow errors and low performance problems. People often use system logs produced by distributed systems for troubleshooting and problem diagnosis. However, manually inspecting system logs to detect anomalies is unfeasible due to the increasing scale and complexity of distributed systems. Therefore, there is a great demand for automatic anomalies detection techniques based on log analysis. In this paper, we propose an unstructured log analysis technique for anomalies detection. In the technique, we propose a novel algorithm to convert free form text messages in log files to log keys without heavily relying on application specific knowledge. The log keys correspond to the log-print statements in the source code which can provide cues of system execution behavior. After converting log messages to log keys, we learn a Finite State Automaton (FSA) from training log sequences to present the normal work flow for each system component. At the same time, a performance measurement model is learned to characterize the normal execution performance based on the log messages' timing information. With these learned models, we can automatically detect anomalies in newly input log files. Experiments on Hadoop and SILK show that the technique can effectively detect running anomalies.