arXiv subjects

Tianyi Sun

Publications and source records attributed to Tianyi Sun.

9 recordsLinked to original sources

arXiv2026

SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents

Agent skills, SKILL files that package reusable procedural knowledge for an LLM agent, are a popular mechanism for extending agent capabilities. Public repositories now host them in large and growing numbers, yet these artifacts are fragmented, redundant, and uneven in quality, and their value in practice is unclear. A core question remains open, namely how to consolidate this open-source SKILL ecosystem into a single usable corpus, and what bounds its benefit on real-world agent tasks. We present SkillCorpus, a framework that aggregates, curates, matches, and evaluates the open skill ecosystem at scale. It filters ~821,000 crawled skills through a multi-stage pipeline into 96,401 skills organised by a 16-class taxonomy and three quality facets (utility, robustness, safety), and pairs them with a fine-tuned retrieval-and-selection stack that matches task-relevant skills. We evaluate end-to-end across three benchmarks (SkillsBench, GDPVal, QwenClawBench), two harnesses, and two open backbones with a frontier robustness check. Integrating SkillCorpus yields consistent gains across all three benchmarks, largest on SkillsBench (+7.5 pp). An operational analysis traces the gains to a coverage boundary and a harness boundary. SkillCorpus is, to our knowledge, the first end-to-end account of when a curated, retrieval-served community corpus improves real agent tasks, and where it does not. The dataset, models, and code are available at https://github.com/EverMind-AI/SkillCorpus.

cs.CL↗

arXiv2026

OrbitBFT: Enabling Scalable and Robust BFT Consensus in LEO Constellations

Low Earth Orbit (LEO) satellite constellations are evolving from communication relays into autonomous platforms operating in increasingly congested and contested environments. Since uplinks to ground stations can be severed or jammed, ensuring reliable coordination among satellites requires autonomous Byzantine Fault-Tolerant (BFT) consensus. However, applying conventional BFT protocols to LEO constellations is challenging due to their dynamic topology, sparse connectivity, and limited communication bandwidth. In this paper, we present OrbitBFT, a novel two-stage hierarchical BFT consensus protocol tailored to the unique characteristics of LEO constellations. First, OrbitBFT exploits the topological stability within orbital planes to partition the constellation and perform localized intra-plane consensus, which reduces communication overhead. Second, we design a Byzantine-resilient bypass mechanism and a hop-by-hop transmission protocol to ensure reliable message delivery and mitigate congestion, even in the presence of adversarial behavior. Third, we adapt and optimize PBFT and HotStuff to the LEO context, achieving linear message complexity while preserving safety and liveness. Extensive evaluations in a realistic Starlink-based simulation demonstrate that OrbitBFT significantly improves scalability, throughput, and latency compared to its original designs, making it a practical and efficient BFT solution for large-scale satellite networks.

cs.DC↗

arXiv2025

Asynchronous BFT Consensus Made Wireless

Asynchronous Byzantine fault-tolerant (BFT) consensus protocols, known for their robustness in unpredictable environments without relying on timing assumptions, are becoming increasingly vital for wireless applications. While these protocols have proven effective in wired networks, their adaptation to wireless environments presents significant challenges. Asynchronous BFT consensus, characterized by its N parallel consensus components (e.g., asynchronous Byzantine agreement, reliable broadcast), suffers from high message complexity, leading to network congestion and inefficiency, especially in resource-constrained wireless networks. Asynchronous Byzantine agreement (ABA) protocols, a foundational component of asynchronous BFT, require careful balancing of message complexity and cryptographic overhead to achieve efficient implementation in wireless settings. Additionally, the absence of dedicated testbeds for asynchronous wireless BFT consensus protocols hinders development and performance evaluation. To address these challenges, we propose a consensus batching protocol (ConsensusBatcher), which supports both vertical and horizontal batching of multiple parallel consensus components. We leverage ConsensusBatcher to adapt three asynchronous BFT consensus protocols (HoneyBadgerBFT, BEAT, and Dumbo) from wired networks to resource-constrained wireless networks. To evaluate the performance of ConsensusBatcher-enabled consensus protocols in wireless environments, we develop and open-source a testbed for deployment and performance assessment of these protocols. Using this testbed, we demonstrate that ConsensusBatcher-based consensus reduces latency by 48% to 59% and increases throughput by 48% to 62% compared to baseline consensus protocols.

cs.DC↗

arXiv2023

Vision Transformer Pruning Via Matrix Decomposition

This is a further development of Vision Transformer Pruning via matrix decomposition. The purpose of the Vision Transformer Pruning is to prune the dimension of the linear projection of the dataset by learning their associated importance score in order to reduce the storage, run-time memory, and computational demands. In this paper we further reduce dimension and complexity of the linear projection by implementing and comparing several matrix decomposition methods while preserving the generated important features. We end up selected the Singular Value Decomposition as the method to achieve our goal by comparing the original accuracy scores in the original Github repository and the accuracy scores of using those matrix decomposition methods, including Singular Value Decomposition, four versions of QR Decomposition, and LU factorization.

cs.CV↗

arXiv2023

Topological Interpretations of GPT-3

This is an experiential study of investigating a consistent method for deriving the correlation between sentence vector and semantic meaning of a sentence. We first used three state-of-the-art word/sentence embedding methods including GPT-3, Word2Vec, and Sentence-BERT, to embed plain text sentence strings into high dimensional spaces. Then we compute the pairwise distance between any possible combination of two sentence vectors in an embedding space and map them into a matrix. Based on each distance matrix, we compute the correlation of distances of a sentence vector with respect to the other sentence vectors in an embedding space. Then we compute the correlation of each pair of the distance matrices. We observed correlations of the same sentence in different embedding spaces and correlations of different sentences in the same embedding space. These observations are consistent with our hypothesis and take us to the next stage.

cs.CL↗

arXiv2023

Greedy Matroid Algorithm And Computational Persistent Homology

An important problem in computational topology is to calculate the homology of a space from samples. In this work, we develop a statistical approach to this problem by calculating the expected rank of an induced map on homology from a sub-sample to the full space. We develop a greedy matroid algorithm for finding an optimal basis for the image of the induced map, and investigate the relationship between this algorithm and the probability of sampling vectors in the image of the induced map.

stat.CO↗

arXiv2023

P-Tensors: a General Formalism for Constructing Higher Order Message Passing Networks

Several recent papers have proposed increasing the expressive power of graph neural networks by exploiting subgraphs or other topological structures. In parallel, researchers have investigated higher order permutation equivariant networks. In this paper we tie these two threads together by providing a general framework for higher order permutation equivariant message passing in subgraph neural networks. In this paper we introduce a new type of mathematical object called $P$-tensors, which provide a simple way to define the most general form of permutation equivariant message passing in both the above two categories of networks. We show that the P-Tensors paradigm can achieve state-of-the-art performance on benchmark molecular datasets.

stat.ML↗

arXiv2023

On the Truth Assignment Theorem of the Language of Sentential Logic

This project contains two chapters. Chapter 2 has two sections. First, we define the well-formed formulas of the Language of Sentential Logic using Construction Sequences. Second, we prove the Truth Assignments using the Language of Sentential Logic. Chapter 3 has two sections. First, we define the Recursion Theorem. Second, we prove the Truth Assignments using a general formulation of the Recursion Theorem.

math.LO↗

arXiv2023

Clustering US Counties to Find Patterns Related to the COVID-19 Pandemic

When COVID-19 first started spreading and quarantine was implemented, the Society for Industrial and Applied Mathematics (SIAM) Student Chapter at the University of Minnesota-Twin Cities began a collaboration with Ecolab to use our skills as data scientists and mathematicians to extract useful insights from relevant data relating to the pandemic. This collaboration consisted of multiple groups working on different projects. In this write-up we focus on using clustering techniques to help us find groups of similar counties in the US and use that to help us understand the pandemic. Our team for this project consisted of University of Minnesota students Cora Brown, Sarah Milstein, Tianyi Sun, and Cooper Zhao, with help from Ecolab Data Scientist Jimmy Broomfield and University of Minnesota student Skye Ke. In the sections below we describe all of the work done for this project. In Section 2, we list the data we gathered, as well as the feature engineering we performed. In Section 3, we describe the metrics we used for evaluating our models. In Section 4, we explain the methods we used for interpreting the results of our various clustering approaches. In Section 5, we describe the different clustering methods we implemented. In Section 6, we present the results of our clustering techniques and provide relevant interpretation. Finally, in Section 7, we provide some concluding remarks comparing the different clustering methods.

cs.LG↗