arXiv subjects

Junhua Zhu

Publications and source records attributed to Junhua Zhu.

7 recordsLinked to original sources

arXiv2026

Meflex: A Multi-agent Scaffolding System for Entrepreneurial Ideation Iteration via Nonlinear Business Plan Writing

Business plan (BP) writing plays a key role in entrepreneurship education by helping learners construct, evaluate, and iteratively refine their ideas. However, conventional BP writing remains a rigid, linear process that often fails to reflect the dynamic and recursive nature of entrepreneurial ideation. This mismatch is particularly challenging for novice entrepreneurial students, who struggle with the substantial cognitive demands of developing and refining ideas. While reflection and meta-reflection are critical strategies for fostering divergent and convergent thinking, existing writing tools rarely scaffold these higher-order processes. To address this gap, we present the Meflex System, a large language model (LLM)-based writing tool that integrates BP writing scaffolding with a nonlinear idea canvas to support iterative ideation through reflection and meta-reflection. We report findings from an exploratory user study with 30 participants that examined the system's usability and cognitive impact. Results show that Meflex effectively scaffolds BP writing, promotes divergent thinking through LLM-supported reflection, and enhances meta-reflective awareness while reducing cognitive load during complex idea development. These findings highlight the potential of non-linear LLM-based writing tools to foster deeper and coherent entrepreneurial thinking.

cs.HC↗

arXiv2026

ParaTutor: Coordinating Parent and Child Math Tutoring through Role Separated LLM Scaffolding

Parent and child tutoring is a collaborative learning setting with asymmetric roles. Parents guide children s problem solving, while children are expected to remain actively engaged in understanding and reasoning. However, most LLM based learning systems are designed for single users or relatively symmetric collaboration, leaving parent and child tutoring with distinct instructional roles underexplored. Through a formative study, we found that parent and child math tutoring was often disrupted by cognitive misalignment, emotional escalation, and method mismatch. To address these challenges, we present ParaTutor, a multiple agents LLM based scaffolding system for home math word problem tutoring. ParaTutor distributes support across user roles by providing parents with strategy, language, repair, and phase scaffolds, while providing children with visual grounding for problem interpretation. We evaluated ParaTutor with 23 parent and child dyads (children aged 10 to 12) across four tutoring conditions that varied how LLM assistance was delivered. Results show that generic LLM assistance often provided useful explanations but did not consistently support parent led tutoring or children s active reasoning. In contrast, ParaTutor helped redistribute tutoring work across parents and children, increased children s engagement with word problems, supported shared understanding through visual grounding, and helped parents translate LLM generated methods into child facing tutoring moves. These findings suggest that in family learning, the value of LLM support depends not only on model capability, but also on how support is coordinated across users with different roles. Our work contributes design implications for LLM systems that support role sensitive scaffolding in parent and child learning.

cs.HC↗

arXiv2026

To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair

LLM-based agents for program repair are increasingly built on a "generate-run-revise" paradigm, iteratively executing tests to evaluate and refine patches. This execution-based approach has become standard practice in state-of-the-art systems. However, executions can be time-consuming and expensive, yet their impact on these agents remains underexplored. In this paper, we conduct a two-stage empirical study over execution behavior in LLM-based program repair. To characterize execution behavior at scale, we first analyze 7,745 agent traces from SWE-bench leaderboard submissions. Second, we evaluate 3,000 end-to-end repair attempts across 200 SWE-bench instances and three agents (Claude Code, Codex, and the open-source OpenCode) under four execution paradigms, which allows for a fine-grained comparison of performance and cost. Our analysis reveals three key observations: (1) Code execution is used across all agents and models analyzed, with an average of 8.8 test runs per task. Execution behavior varies substantially across agents and models, with frequency ranging from 2 to 19 per task, and late-stage executions consistently achieve higher success rates than early-stage ones. (2) Execution restrictions have little effect on repair success: on commercial agents with SOTA models the resolve-rate gap between Prohibited and Unrestricted is only 1.25 percentage points and not statistically significant, while Prohibited saves substantial token and wall-clock cost. (3) Execution benefit is concentrated rather than uniform. These patterns suggest that current agents apply execution indiscriminately, paying its cost on instances where it provides little benefit. Execution, therefore, should be treated as a resource with an explicit cost-benefit tradeoff, not a default capability.

cs.SE↗

arXiv2025

Designing the Future of Entrepreneurship Education: Exploring an AI-Empowered Scaffold System for Business Plan Development

Entrepreneurship education equips students to transform innovative ideas into actionable entrepreneurship plans, yet traditional approaches often struggle to provide the personalized guidance and practical alignment needed for success. Focusing on the business plan as a key learning tool and evaluation method, this study investigates the design needs for an AI-empowered scaffold system to address these challenges. Based on qualitative insights from educators and students, the findings highlight three critical dimensions for system design: mastery of business plan development, alignment with entrepreneurial learning goals, and integration of adaptive system features. These findings underscore the transformative potential of AI in bridging gaps in entrepreneurship education while emphasizing the enduring value of human mentorship and experiential learning.

cs.HC↗

arXiv2024

FusionANNS: An Efficient CPU/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. We present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system -- SPANN and GPU-accelerated in-memory ANNS system -- RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1X higher query per second (QPS) and 5.7-8.8X higher cost efficiency compared with SPANN; 2) and 2-4.9X higher QPS and 2.3-6.8X higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

cs.IR↗

arXiv2023

NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streams

Existing Graph Neural Network (GNN) training frameworks have been designed to help developers easily create performant GNN implementations. However, most existing GNN frameworks assume that the input graphs are static, but ignore that most real-world graphs are constantly evolving. Though many dynamic GNN models have emerged to learn from evolving graphs, the training process of these dynamic GNNs is dramatically different from traditional GNNs in that it captures both the spatial and temporal dependencies of graph updates. This poses new challenges for designing dynamic GNN training frameworks. First, the traditional batched training method fails to capture real-time structural evolution information. Second, the time-dependent nature makes parallel training hard to design. Third, it lacks system supports for users to efficiently implement dynamic GNNs. In this paper, we present NeutronStream, a framework for training dynamic GNN models. NeutronStream abstracts the input dynamic graph into a chronologically updated stream of events and processes the stream with an optimized sliding window to incrementally capture the spatial-temporal dependencies of events. Furthermore, NeutronStream provides a parallel execution engine to tackle the sequential event processing challenge to achieve high performance. NeutronStream also integrates a built-in graph storage structure that supports dynamic updates and provides a set of easy-to-use APIs that allow users to express their dynamic GNNs. Our experimental results demonstrate that, compared to state-of-the-art dynamic GNN implementations, NeutronStream achieves speedups ranging from 1.48X to 5.87X and an average accuracy improvement of 3.97%.

cs.LG↗

arXiv2016

Parallel Stream Processing Against Workload Skewness and Variance

Key-based workload partitioning is a common strategy used in parallel stream processing engines, enabling effective key-value tuple distribution over worker threads in a logical operator. While randomized hashing on the keys is capable of balancing the workload for key-based partitioning when the keys generally follow a static distribution, it is likely to generate poor balancing performance when workload variance occurs on the incoming data stream. This paper presents a new key-based workload partitioning framework, with practical algorithms to support dynamic workload assignment for stateful operators. The framework combines hash-based and explicit key-based routing strategies for workload distribution, which specifies the destination worker threads for a handful of keys and assigns the other keys with the hashing function. When short-term distribution fluctuations occur to the incoming data stream, the system adaptively updates the routing table containing the chosen keys, in order to rebalance the workload with minimal migration overhead within the stateful operator. We formulate the rebalance operation as an optimization problem, with multiple objectives on minimizing state migration costs, controlling the size of the routing table and breaking workload imbalance among worker threads. Despite of the NP-hardness nature behind the optimization formulation, we carefully investigate and justify the heuristics behind key (re)routing and state migration, to facilitate fast response to workload variance with ignorable cost to the normal processing in the distributed system. Empirical studies on synthetic data and real-world stream applications validate the usefulness of our proposals and prove the huge advantage of our approaches over state-of-the-art solutions in the literature.

cs.DC↗