Author name cluster

Shilin He

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

TMLR Journal 2025 Journal Article

Large Action Models: From Inception to Implementation

Lu Wang
Fangkai Yang
Chaoyun Zhang
Junting Lu
Jiaxu Qian
Shilin He
Pu Zhao
Bo Qiao

As AI continues to advance, there is a growing demand for systems that go beyond language-based assistance and move toward intelligent agents capable of performing real-world actions. This evolution requires the transition from traditional Large Language Models (LLMs), which excel at generating textual responses, to Large Action Models (LAMs), designed for action generation and execution within dynamic environments. Enabled by agent systems, LAMs hold the potential to transform AI from passive language understanding to active task completion, marking a significant milestone in the progression toward artificial general intelligence. In this paper, we present a comprehensive framework for developing LAMs, offering a systematic approach to their creation, from inception to deployment. We begin with an overview of LAMs, highlighting their unique characteristics and delineating their differences from LLMs. Using a Windows OS-based agent as a case study, we provide a detailed, step-by-step guide on the key stages of LAM development, including data collection, model training, environment integration, grounding, and evaluation. This generalizable workflow can serve as a blueprint for creating functional LAMs in various application domains. We conclude by identifying the current limitations of LAMs and discussing directions for future research and industrial deployment, emphasizing the challenges and opportunities that lie ahead in realizing the full potential of LAMs in real-world applications.

PDF Details

TMLR Journal 2025 Journal Article

Large Language Model-Brained GUI Agents: A Survey

Chaoyun Zhang
Shilin He
Jiaxu Qian
Bowen Li
Liqun Li
Si Qin
Yu Kang
Minghua Ma

Graphical User Interfaces (GUIs) have long been central to human-computer interaction, providing an intuitive and visually-driven way to access and interact with digital systems. Traditionally, automating GUI interactions relied on script-based or rule-based approaches, which, while effective for fixed workflows, lacked the flexibility and adaptability required for dynamic, real-world applications. The advent of Large Language Models (LLMs), particularly multimodal models, has ushered in a new era of GUI automation. They have demonstrated exceptional capabilities in natural language understanding, code generation, task generalization, and visual processing. This has paved the way for a new generation of ''LLM-brained'' GUI agents capable of interpreting complex GUI elements and autonomously executing actions based on natural language instructions. These agents represent a paradigm shift, enabling users to perform intricate, multi-step tasks through simple conversational commands. Their applications span across web navigation, mobile app interactions, and desktop automation, offering a transformative user experience that revolutionizes how individuals interact with software. This emerging field is rapidly advancing, with significant progress in both research and industry. To provide a structured understanding of this trend, this paper presents a comprehensive survey of LLM-brained GUI agents, exploring their historical evolution, core components, and advanced techniques. We address critical research questions such as existing GUI agent frameworks, the collection and utilization of data for training specialized GUI agents, the development of large action models tailored for GUI tasks, and the evaluation metrics and benchmarks necessary to assess their effectiveness. Additionally, we examine emerging applications powered by these agents. Through a detailed analysis, this survey identifies key research gaps and outlines a roadmap for future advancements in the field. By consolidating foundational knowledge and state-of-the-art developments, this work aims to guide both researchers and practitioners in overcoming challenges and unlocking the full potential of LLM-brained GUI agents. We anticipate that this survey will serve both as a practical cookbook for constructing LLM-powered GUI agents, and as a definitive reference for advancing research in this rapidly evolving domain.

PDF Details

ICLR Conference 2025 Conference Paper

OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

Junjielong Xu
Qinan Zhang
Zhiqing Zhong
Shilin He
Chaoyun Zhang
Qingwei Lin
Dan Pei
Pinjia He

Large language models (LLMs) are driving substantial advancements in software engineering, with successful applications like Copilot and Cursor transforming real-world development practices. However, current research predominantly focuses on the early stages of development, such as code generation, while overlooking the post-development phases that are crucial to user experience. To explore the potential of LLMs in this direction, we propose OpenRCA, a benchmark dataset and evaluation framework for assessing LLMs’ ability to identify the root cause of software failures. OpenRCA includes 335 failures from three enterprise software systems, along with over 68 GB of telemetry data (logs, metrics, and traces). Given a failure case and its associated telemetry, the LLM is tasked to identify the root cause that triggered the failure, requiring comprehension of software dependencies and reasoning over heterogeneous, long-context telemetry data. Our results show substantial room for improvement, as current models can only handle the simplest cases. Even with the specially designed RCA-agent, the best-performing model, Claude 3.5, solved only 11.34% failure cases. Our work paves the way for future research in this direction.

Details

NeurIPS Conference 2025 Conference Paper

SWE-bench Goes Live!

LingHao Zhang
Shilin He
Chaoyun Zhang
Yu Kang
Bowen Li
Chengxing Xie
Junhao Wang
Maoquan Wang

The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a key benchmark for evaluating the capabilities of large language models (LLMs). While SWE-bench has become the dominant benchmark in this domain, it suffers from several limitations: it has not been updated since its release, is restricted to only 12 repositories, and relies heavily on manual effort for constructing test instances and setting up executable environments, significantly limiting its scalability. We present SWE-bench-Live, a live-updatable benchmark designed to address these limitations. SWE-bench-Live currently includes 1, 890 tasks derived from real GitHub issues created since 2024, spanning 223 repositories. Each task is accompanied by a dedicated Docker image to ensure reproducible execution. Additionally, we introduce an automated curation pipeline that streamlines the entire process from instance creation to environment setup, removing manual bottlenecks and enabling scalability and continuous updates. We evaluate a range of state-of-the-art models and agent frameworks on SWE-bench-Live, offering detailed empirical insights into their real-world bug-fixing capabilities. By providing a fresh, diverse, and executable benchmark grounded in live repository activity, SWE-bench-Live supports reliable, large-scale assessment of code LLMs and code agents in realistic development settings.

PDF Details

AIIM Journal 2024 Journal Article

Enhanced ICD-10 code assignment of clinical texts: A summarization-based approach

Yaoqian Sun
Lei Sang
Dan Wu
Shilin He
Yani Chen
Huilong Duan
Han Chen
Xudong Lu

Background Assigning International Classification of Diseases (ICD) codes to clinical texts is a common and crucial practice in patient classification, hospital management, and further statistics analysis. Current auto-coding methods mainly transfer this task to a multi-label classification problem. Such solutions are suffering from high-dimensional mapping space and excessive redundant information in long clinical texts. To alleviate such a situation, we introduce text summarization methods to the ICD coding regime and apply text matching to select ICD codes. Method We focus on the tenth revision of the ICD (ICD-10) coding and design a novel summarization-based approach (SuM) with an end-to-end strategy to efficiently assign ICD-10 code to clinical texts. In this approach, a knowledge-guided pointer network is purposed to distill and summarize key information in clinical texts precisely. Then a matching model with matching-aggregation architecture follows to align the summary result with code, tuning the one-vs-all scenario to one-vs-one matching so that the large-label-space obstacle laid in classification approaches would be avoided. Result The 12, 788 ICD-10 coded discharge summaries from a Chinese hospital were collected to evaluate the proposed approach. Compared with existing methods, the purposed model achieves the greatest coding results with Micro AUC of 0. 9548, MRR@10 of 0. 7977, Precision@10 of 0. 0944, and Recall@10 of 0. 9439 for the TOP-50 Dataset. Results on the FULL-Dataset remain consistent. Also, the proposed knowledge encoder and applied end-to-end strategy are proven to facilitate the whole model to gain efficacy in selecting the most suitable code. Conclusion The proposed automatic ICD-10 code assignment approach via text summarization can effectively capture critical messages in long clinical texts and improve the performance of ICD-10 coding of clinical texts.

Details DOI

ICLR Conference 2023 Conference Paper

Towards Lightweight, Model-Agnostic and Diversity-Aware Active Anomaly Detection

Xu Zhang 0024
Yuan Zhao 0014
Ziang Cui
Liqun Li
Shilin He
Qingwei Lin
Yingnong Dang
Saravan Rajmohan

Active Anomaly Discovery (AAD) is flourishing in the anomaly detection research area, which aims to incorporate analysts’ feedback into unsupervised anomaly detectors. However, existing AAD approaches usually prioritize the samples with the highest anomaly scores for user labeling, which hinders the exploration of anomalies that were initially ranked lower. Besides, most existing AAD approaches are specially tailored for a certain unsupervised detector, making it difficult to extend to other detection models. To tackle these problems, we propose a lightweight, model-agnostic and diversity-aware AAD method, named LMADA. In LMADA, we design a diversity-aware sample selector powered by Determinantal Point Process (DPP). It considers the diversity of samples in addition to their anomaly scores for feedback querying. Furthermore, we propose a model-agnostic tuner. It approximates diverse unsupervised detectors with a unified proxy model, based on which the feedback information is incorporated by a lightweight non-linear representation adjuster. Through extensive experiments on 8 public datasets, LMADA achieved 74% F1-Score improvement on average, outperforming other comparative AAD approaches. Besides, LMADA can also achieve significant performance boosting under any unsupervised detectors.

Details