English
Related papers

Related papers: Graph-of-Skills: Dependency-Aware Structural Retri…

200 papers

Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill…

Computation and Language · Computer Science 2026-05-29 Jiahao Ying , Boxian Ai , Wei Tang , Siyuan Liu , Yixin Cao

Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a…

Computation and Language · Computer Science 2026-04-28 Xinyi Huang

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Zuyao Chen , Jinlin Wu , Zhen Lei , Marc Pollefeys , Chang Wen Chen

Recent advances in Large Language Models (LLMs) have demonstrated the emergence of capabilities (learned skills) when the number of system parameters and the size of training data surpass certain thresholds. The exact mechanisms behind such…

Computation and Language · Computer Science 2025-07-17 Kuo-Yu Liao , Cheng-Shang Chang , Y. -W. Peter Hong

With an ever-growing zoo of LLMs and benchmarks, the need to orchestrate multiple models for improved task performance has never been more pressing. While frameworks like Mixture-of-Agents (MoA) attempt to coordinate LLMs, they often fall…

Artificial Intelligence · Computer Science 2026-04-21 Sukwon Yun , Jie Peng , Pingzhi Li , Wendong Fan , Jie Chen , James Zou , Guohao Li , Tianlong Chen

LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool…

Artificial Intelligence · Computer Science 2026-04-23 Hao Liu , Dongyu Li

Although Large Language Models (LLMs) have demonstrated potential in processing graphs, they struggle with comprehending graphical structure information through prompts of graph description sequences, especially as the graph size increases.…

Computation and Language · Computer Science 2024-12-17 Yukun Cao , Shuo Han , Zengyi Gao , Zezhong Ding , Xike Xie , S. Kevin Zhou

Offline goal-conditioned reinforcement learning (GCRL) often struggles with long-horizon tasks, where errors in value estimation accumulate and produce unreliable policies. It is typically assumed that effective long-term planning is…

Machine Learning · Computer Science 2026-05-26 Evgenii Opryshko , Junwei Quan , Claas Voelcker , Yilun Du , Igor Gilitschenski

While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate. This limitation reduces the accuracy of answering questions based on…

Machine Learning · Computer Science 2025-03-31 Song Wang , Junhong Lin , Xiaojie Guo , Julian Shun , Jundong Li , Yada Zhu

Improving the performance of large language models (LLMs) in complex question-answering (QA) scenarios has always been a research focal point. Recent studies have attempted to enhance LLMs' performance by combining step-wise planning with…

Computation and Language · Computer Science 2024-10-24 Junjie Wang , Mingyang Chen , Binbin Hu , Dan Yang , Ziqi Liu , Yue Shen , Peng Wei , Zhiqiang Zhang , Jinjie Gu , Jun Zhou , Jeff Z. Pan , Wen Zhang , Huajun Chen

Large language models (LLMs) offer new opportunities for constructing knowledge graphs (KGs) from unstructured clinical narratives. However, existing approaches often rely on structured inputs and lack robust validation of factual accuracy…

Artificial Intelligence · Computer Science 2026-01-06 Udiptaman Das , Krishnasai B. Atmakuri , Duy Ho , Chi Lee , Yugyung Lee

Large Language Model (LLM) agents have shown stunning results in complex tasks, yet they often operate in isolation, failing to learn from past experiences. Existing memory-based methods primarily store raw trajectories, which are often…

Retrieval-augmented generation (RAG) has revitalized Large Language Models (LLMs) by injecting non-parametric factual knowledge. Compared with long-context LLMs, RAG is considered an effective summarization tool in a more concise and…

Computation and Language · Computer Science 2025-05-30 Haozhen Zhang , Tao Feng , Jiaxuan You

Understanding large software systems is a challenging task, especially when code is distributed across multiple repositories and microservices. Developers often need to reason not only about the structure of the code, but also about its…

Software Engineering · Computer Science 2026-01-19 Niko Usai , Dario Montagnini , Kristian Ilianov Iliev , Raffaele Camanzo

Recently, the emergence of large language models (LLMs) has motivated integrating language descriptions into graphs, forming text-attributed graphs (TAGs) that enhance model encoding capabilities from a data-centric perspective. A review of…

Machine Learning · Computer Science 2026-02-03 Zhihan Zhang , Xunkai Li , Lei Zhu , Guang Zeng , Bowen Fan , Yanzhe Wen , Hongchao Qin , Rong-Hua Li , Guoren Wang

Graphs with abundant attributes are essential in modeling interconnected entities and enhancing predictions across various real-world applications. Traditional Graph Neural Networks (GNNs) often require re-training for different graph tasks…

Computation and Language · Computer Science 2026-05-26 Yanchao Tan , Hang Lv , Pengxiang Zhan , Shiping Wang , Carl Yang

Repository aware coding agents often struggle to recover build and test structure, especially in multilingual projects where cross language dependencies are encoded across heterogeneous build systems and tooling. We introduce the Repository…

Software Engineering · Computer Science 2026-01-16 Tsvi Cherny-Shahar , Amiram Yehudai

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle…

Machine Learning · Computer Science 2023-12-05 Haoqi Yuan , Chi Zhang , Hongcheng Wang , Feiyang Xie , Penglin Cai , Hao Dong , Zongqing Lu

Transformer neural networks show promising capabilities, in particular for uses in materials analysis, design and manufacturing, including their capacity to work effectively with both human language, symbols, code, and numerical data. Here…

Computation and Language · Computer Science 2023-11-01 Markus J. Buehler

Large language models show great potential in unstructured data understanding, but still face significant challenges with graphs due to their structural hallucination. Existing approaches mainly either verbalize graphs into natural…

Computation and Language · Computer Science 2026-02-03 Jingyao Wu , Bin Lu , Zijun Di , Xiaoying Gan , Meng Jin , Luoyi Fu , Xinbing Wang , Chenghu Zhou