arXiv subjects

Zijian Ding

Publications and source records attributed to Zijian Ding.

At least 19 recordsLinked to original sources

arXiv2026

Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge

Sustained deployment of generative AI agents requires more than isolated task success. Agents must remain useful across repeated interactions, changing conditions, and dependencies on people within shared workflows, especially as technical, human, and operational disruptions accumulate over time. We propose operational resilience and considerate participation as two complementary aspects of evaluating such agents: the former captures how agents recover from blocked work while preserving progress and communicating their limits, and the latter captures how their adaptation accounts for affected people, role boundaries, and the surrounding workflow. Yet both remain underexplored under accumulating challenge. We study 120 simulated healthcare trajectories across two generative AI models and twelve stakeholder-derived tasks under light, medium, and heavy challenge. We compare textual action plans, prompted internal assessments, and quantitative structured workload and affect reports to examine how agent behavior and reported state change as challenge accumulates. Regarding operational resilience, agents shift from self-directed recovery toward greater human dependence, while reporting increasing workload and negative affect in structured reports but seldom expressing strain in textual responses. Regarding considerate participation, agents broaden from task-focused adaptation toward task reframing, attention to others, role-boundary adjustment, and wider coordination, with distinct patterns across actions and internal assessments. From these findings, we derive five deployment dilemmas involving persistence, attention, role boundaries, state disclosure, and escalation that require stakeholder specification, further informing technical implications for learning, situated evaluation, and embodied adaptation.

cs.AI↗

arXiv2026

AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and Performance

High-Level Synthesis (HLS) provides a fast path from concepts to silicon, but converting real-world software into synthesizable HLS code remains challenging due to restrictive language support and the gap between software and hardware programming practices. Existing automated and LLM-based refactoring approaches partially address this problem, yet they often lack flexibility, struggle to scale, and incur high computational costs. We introduce AgRefactor, an LLM-based multi-agent workflow for refactoring software into HLS-compatible programs. AgRefactor incorporates a self-evolving memory system that accumulates and retrieves factual and strategic knowledge across tasks, improving robustness and efficiency on unseen programs. To reduce cost and enhance scalability, it integrates automated refactoring tools, enabling agents to balance LLM-driven rewrites with efficient tool-based transformations. On 9 out of 11 challenging real-world benchmarks, which are 5-10x longer than the most complex cases studied in prior work, AgRefactor outperforms or matches the state-of-the-art automated refactoring tool and a strong LLM-based baseline built on the same framework backbone. Further agentic performance optimization yields a 6.51x geometric mean speedup over the SoTA pragma tuning tool and a 1.20x speedup over optimized open-source designs with less than 20% extra resources. AgRefactor is fully-automated and open-sourced.

cs.AI↗

arXiv2026

ResearchCube: Multi-Dimensional Trade-off Exploration for Research Ideation

Research ideation requires navigating trade-offs across multiple evaluative dimensions, yet most AI-assisted ideation tools leave this multi-dimensional reasoning unsupported, or reducing evaluation to unipolar scales where "more is better". We present ResearchCube, a system that reframes evaluation dimensions as bipolar trade-off spectra (e.g., theory-driven vs. data-driven) and renders research ideas as manipulable points in a user-constructed 3D evaluation space. Given a research intent, the system proposes candidate bipolar dimension pairs; users select up to three to define the axes of a personalized evaluation cube. Four spatial interactions -- AI-scaffolded dimension generation, 3D navigation with face snapping, drag-based idea steering, and drag-based synthesis -- enable researchers to explore and refine ideas through direct manipulation rather than text prompts. A qualitative study with 11 researchers revealed that (1) bipolar dimensions served as cognitive scaffolds that externalized evaluative thinking and offloaded working memory, (2) the spatial representation provided a sense of agency absent in chatbot-based AI tools, (3) participants desired fluid transitions across dimensionality levels -- from single-dimension focus to more than three dimensions, and (4) a productive tension emerged between AI-suggested starting dimensions and users' evolving desire for control. We distill these findings into design implications for multi-dimensional research ideation tools, including progressive dimensional control, fluid dimensionality, and transparent synthesis with provenance.

cs.HC↗

arXiv2026

Towards Considerate Human-Robot Coexistence: A Dual-Space Framework of Robot Design and Human Perception in Healthcare

The rapid advancement of robotics is reshaping what it means for humans and robots to coexist -- through expanded capabilities, more intuitive interactions, and deeper integration into real-world workflows. Beyond sharing physical space, this coexistence is increasingly characterized by organizational embeddedness, temporal evolution, social situatedness, and open-ended uncertainty. Because such coexistence extends beyond a single encounter, understanding healthcare robots requires looking beyond initial acceptance to how stakeholders' perceptions evolve through continued engagement. Yet, prior work has largely relied on single-point snapshots of attitudes and acceptance, offering limited insight into coexistence as a long-term, dynamic process. We address these gaps through in-depth follow-up interviews with nine participants from a 14-week co-design study on healthcare robots. We identify the human perception space, which includes four interpretive dimensions (i.e., degree of decomposition, source of evidence, scope of reasoning, and temporal orientation). We enrich the conceptual framework of human-robot coexistence by conceptualizing the mutual relationship between the human perception space and the robot design space as a co-evolving loop, in which human needs, design decisions, situated interpretations, and social mediation continuously reshape one another over time. Building on this, we propose considerate human-robot coexistence, arguing that humans act not only as design contributors but also as interpreters and mediators who actively shape how robots are understood and integrated across deployment stages. Our related prior work and supplementary materials, including the interview protocol, are available at https://byc-sophie.github.io/considerate-human-robot-coexistence/

cs.RO↗

arXiv2026

StreetDesignAI: Broadening Designer Perspectives Through Multi-Persona Evaluation of Cycling Infrastructure

Designing cycling infrastructure requires balancing the competing needs of diverse user groups, yet designers often struggle to anticipate how different cyclists experience the same street environment. We investigate how persona-based evaluation can support cycling infrastructure design by making experiential conflicts explicit during the design process. Informed by a formative study with 12 domain experts and crowdsourced bikeability assessments from 427 cyclists, we present StreetDesignAI, an interactive system that enables designers to (1) ground evaluation in real street context through imagery and map data, (2) receive parallel feedback from simulated cyclist personas spanning confident to cautious users, and (3) iteratively modify designs while the system surfaces conflicts across perspectives. A within-subjects study with 26 transportation professionals comparing StreetDesignAI against a general-purpose AI chatbot demonstrates that structured multi-perspective feedback significantly Broaden designers' understanding of various cyclists' perspectives, ability to identify diverse persona needs, and confidence in translating those needs into design decisions. Participants also reported significantly higher overall satisfaction and stronger intention to use the system in professional practice. Qualitative findings further illuminate how explicit conflict surfacing transforms design exploration from single-perspective optimization toward deliberate trade-off reasoning. We discuss implications for AI-assisted tools that scaffold persona-aware design through disagreement as an interaction primitive.

cs.HC↗

arXiv2025

Towards AI as Colleagues: Multi-Agent System Improves Structured Ideation Processes

Most AI systems today are designed to manage tasks and execute predefined steps. This makes them effective for process coordination but limited in their ability to engage in joint problem-solving with humans or contribute new ideas. We introduce MultiColleagues, a multi-agent conversational system that shows how AI agents can act as colleagues by conversing with each other, sharing new ideas, and actively involving users in collaborative ideation processes. In a within-subjects study with 20 participants, we compared MultiColleagues to a single-agent baseline. Results show that MultiColleagues fostered stronger perceived social presence, and participants rated their outcomes as higher in quality and novelty, with more elaboration during ideation. These findings demonstrate the potential of AI agents to move beyond process partners toward colleagues that share intent, strengthen group dynamics, and collaborate with humans to advance ideas.

cs.HC↗

arXiv2025

Spatial Balancing: Designing an LLM-Powered Spatial Externalization Interface for Iterative Science Communication Writing

Science communication revision requires writers to dynamically balance scientific exposition and narrative engagement - a process where writers often struggle with competing directions. Existing LLM-assisted tools help with co-writing, but offer limited support for navigating this iterative, multi-directional revision process. To address this gap, we designed Spatial Balancing, an exploratory revision environment that maps rhetorical goals and revision strategies onto a two-dimensional spatial canvas for experienced science communication creators with domain expertise but lacking formal professional training. By building a design space of communication strategies and embedding them into a spatial exploratory canvas, our system treats feedback as navigational cues rather than prescriptive judgments. Our findings show that this integrated revision environment helps writers stay focused on writing goals, reason about revision as trajectories, and explore alternatives, which supports greater metacognitive control and confidence without increasing workload. This work highlights the value of spatially externalized revision environments for supporting iterative, reflective thinking during LLM-assisted writing.

cs.HC↗

arXiv2025

CareerPooler: AI-Powered Metaphorical Pool Simulation Improves Experience and Outcomes in Career Exploration

Career exploration is uncertain, requiring decisions with limited information and unpredictable outcomes. While generative AI offers new opportunities for career guidance, most systems rely on linear chat interfaces that produce overly comprehensive and idealized suggestions, overlooking the non-linear and effortful nature of real-world trajectories. We present CareerPooler, a generative AI-powered system that employs a pool-table metaphor to simulate career development as a spatial and narrative interaction. Users strike balls representing milestones, skills, and random events, where hints, collisions, and rebounds embody decision-making under uncertainty. In a within-subjects study with 24 participants, CareerPooler significantly improved engagement, information gain, satisfaction, and career clarity compared to a chatbot baseline. Qualitative findings show that spatial-narrative interaction fosters experience-based learning, resilience through setbacks, and reduced psychological burden. Our findings contribute to the design of AI-assisted career exploration systems and more broadly suggest that visually grounded analogical interactions can make generative systems engaging and satisfying.

cs.HC↗

arXiv2025

Frontend Diffusion: Empowering Self-Representation of Junior Researchers and Designers Through Multi-agent System

With the continuous development of generative AI's logical reasoning abilities, AI's growing code-generation potential poses challenges for both technical and creative professionals. But how can these advances be directed toward empowering junior researchers and designers who often require additional help to build and express their professional and personal identities? We introduce Frontend Diffusion, a multi-agent coding system transforming user-drawn layouts and textual prompts into refined website code, thereby supporting self-representation goals. A user study with 13 junior researchers and designers shows AI as a human capability enhancer rather than a replacement, and highlights the importance of bidirectional human-AI alignment. We then discuss future work such as leveraging AI for career development and fostering bidirectional human-AI alignment of multi-agent systems.

cs.HC↗

arXiv2025

Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation

As humans move toward collaborating with coordinated robot teams, understanding how these teams coordinate and fail is essential for building trust and ensuring safety. However, exposing human collaborators to coordination failures during early-stage development is costly and risky, particularly in high-stakes domains such as healthcare. We adopt an agent-simulation approach in which all team roles, including the supervisory manager, are instantiated as LLM agents, allowing us to diagnose coordination failures before humans join the team. Using a controllable healthcare scenario, we conduct two studies with different hierarchical configurations to analyze coordination behaviors and failure patterns. Our findings reveal that team structure, rather than contextual knowledge or model capability, constitutes the primary bottleneck for coordination, and expose a tension between reasoning autonomy and system stability. By surfacing these failures in simulation, we prepare the groundwork for safe human integration. These findings inform the design of resilient robot teams with implications for process-level evaluation, transparent coordination protocols, and structured human integration. Supplementary materials, including codes, task agent setup, trace outputs, and annotated examples of coordination failures and reasoning behaviors, are available at: https://byc-sophie.github.io/mas-to-mars/.

cs.RO↗

arXiv2025

Iceberg: Enhancing HLS Modeling with Synthetic Data

Deep learning-based prediction models for High-Level Synthesis (HLS) of hardware designs often struggle to generalize. In this paper, we study how to close the generalizability gap of these models through pretraining on synthetic data and introduce Iceberg, a synthetic data augmentation approach that expands both large language model (LLM)-generated programs and weak labels of unseen design configurations. Our weak label generation method is integrated with an in-context model architecture, enabling meta-learning from actual and proximate labels. Iceberg improves the geometric mean modeling accuracy by $86.4\%$ when adapt to six real-world applications with few-shot examples and achieves a $2.47\times$ and a $1.12\times$ better offline DSE performance when adapting to two different test datasets. Our open-sourced code is here: https://github.com/UCLA-VAST/iceberg

cs.LG↗

arXiv2025

From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context

Advancements in generative models have enabled multi-agent systems (MAS) to perform complex virtual tasks such as writing and code generation, which do not generalize well to physical multi-agent robotic teams. Current frameworks often treat agents as conceptual task executors rather than physically embodied entities, and overlook critical real-world constraints such as spatial context, robotic capabilities (e.g., sensing and navigation). To probe this gap, we reconfigure and stress-test a hierarchical multi-agent robotic team built on the CrewAI framework in a simulated emergency department onboarding scenario. We identify five persistent failure modes: role misalignment; tool access violations; lack of in-time handling of failure reports; noncompliance with prescribed workflows; bypassing or false reporting of task completion. Based on this analysis, we propose three design guidelines emphasizing process transparency, proactive failure recovery, and contextual grounding. Our work informs the development of more resilient and robust multi-agent robotic systems (MARS), including opportunities to extend virtual multi-agent frameworks to the real world.

cs.RO↗

arXiv2025

LLM-DSE: Searching Accelerator Parameters with LLM Agents

Even though high-level synthesis (HLS) tools mitigate the challenges of programming domain-specific accelerators (DSAs) by raising the abstraction level, optimizing hardware directive parameters remains a significant hurdle. Existing heuristic and learning-based methods struggle with adaptability and sample efficiency. We present LLM-DSE, a multi-agent framework designed specifically for optimizing HLS directives. Combining LLM with design space exploration (DSE), our explorer coordinates four agents: Router, Specialists, Arbitrator, and Critic. These multi-agent components interact with various tools to accelerate the optimization process. LLM-DSE leverages essential domain knowledge to identify efficient parameter combinations while maintaining adaptability through verbal learning from online interactions. Evaluations on the HLSyn dataset demonstrate that LLM-DSE achieves substantial $2.55\times$ performance gains over state-of-the-art methods, uncovering novel designs while reducing runtime. Ablation studies validate the effectiveness and necessity of the proposed agent interactions. Our code is open-sourced here: https://github.com/Nozidoali/LLM-DSE.

cs.AR↗

arXiv2025

Learning to Compare Hardware Designs for High-Level Synthesis

High-level synthesis (HLS) is an automated design process that transforms high-level code into hardware designs, enabling the rapid development of hardware accelerators. HLS relies on pragmas, which are directives inserted into the source code to guide the synthesis process, and pragmas have various settings and values that significantly impact the resulting hardware design. State-of-the-art ML-based HLS methods, such as HARP, first train a deep learning model, typically based on graph neural networks (GNNs) applied to graph-based representations of the source code and pragmas. They then perform design space exploration (DSE) to explore the pragma design space, rank candidate designs using the model, and return the top designs. However, traditional DSE methods face challenges due to the highly nonlinear relationship between pragma settings and performance metrics, along with complex interactions between pragmas that affect performance in non-obvious ways. To address these challenges, we propose compareXplore, a novel approach that learns to compare hardware designs for effective HLS optimization. CompareXplore introduces a hybrid loss function that combines pairwise preference learning with pointwise performance prediction, enabling the model to capture both relative preferences and absolute performance. Moreover, we introduce a novel node difference attention module that focuses on the most informative differences between designs, enabling the model to identify critical pragmas impacting performance. CompareXplore adopts a two-stage DSE, where a pointwise prediction model is used for the initial design pruning, followed by a pairwise comparison stage for precise performance verification. In extensive experiments, compareXplore achieves significant improvements in ranking metrics and generates high-quality HLS results for the selected designs, outperforming the existing SOTA method.

cs.LG↗

arXiv2025

LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning

FPGAs are increasingly adopted in datacenter environments for their reconfigurability and energy efficiency. High-Level Synthesis (HLS) tools have eased FPGA programming by raising the abstraction level from RTL to untimed C/C++, yet attaining high performance still demands expert knowledge and iterative manual insertion of optimization pragmas to modify the microarchitecture. To address this challenge, we propose LIFT, a large language model (LLM)-based coding assistant for HLS that automatically generates performance-critical pragmas given a C/C++ design. We fine-tune the LLM by tightly integrating and supervising the training process with a graph neural network (GNN), combining the sequential modeling capabilities of LLMs with the structural and semantic understanding of GNNs necessary for reasoning over code and its control/data dependencies. On average, LIFT produces designs that improve performance by 3.52x and 2.16x than prior state-of the art AutoDSE and HARP respectively, and 66x than GPT-4o.

cs.LG↗

arXiv2025

"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation

Data analysis encompasses a spectrum of tasks, from high-level conceptual reasoning to lower-level execution. While AI-powered tools increasingly support execution tasks, there remains a need for intelligent assistance in conceptual tasks. This paper investigates the design of an ordered node-link tree interface augmented with AI-generated information hints and visualizations, as a potential shared representation for hypothesis exploration. Through a design probe (n=22), participants generated diagrams averaging 21.82 hypotheses. Our findings showed that the node-link diagram acts as "guardrails" for hypothesis exploration, facilitating structured workflows, providing comprehensive overviews, and enabling efficient backtracking. The AI-generated information hints, particularly visualizations, aided users in transforming abstract ideas into data-backed concepts while reducing cognitive load. We further discuss how node-link diagrams can support both parallel exploration and iterative refinement in hypothesis formulation, potentially enhancing the breadth and depth of human-AI collaborative data analysis.

cs.HC↗

arXiv2025

Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis

High-level synthesis (HLS) is a widely used tool in designing Field Programmable Gate Array (FPGA). HLS enables FPGA design with software programming languages by compiling the source code into an FPGA circuit. The source code includes a program (called "kernel") and several pragmas that instruct hardware synthesis, such as parallelization, pipeline, etc. While it is relatively easy for software developers to design the program, it heavily relies on hardware knowledge to design the pragmas, posing a big challenge for software developers. Recently, different machine learning algorithms, such as GNNs, have been proposed to automate the pragma design via performance prediction. However, when applying the trained model on new kernels, the significant domain shift often leads to unsatisfactory performance. We propose a more domain-generalizable model structure: a two-level hierarchical Mixture of Experts (MoE), that can be flexibly adapted to any GNN model. Different expert networks can learn to deal with different regions in the representation space, and they can utilize similar patterns between the old kernels and new kernels. In the low-level MoE, we apply MoE on three natural granularities of a program: node, basic block, and graph. The high-level MoE learns to aggregate the three granularities for the final decision. To train the hierarchical MoE stably, we further propose a two-stage training method to avoid expert polarization. Extensive experiments verify the effectiveness of the proposed hierarchical MoE. We publicized our codes at https://github.com/weikai-li/HierarchicalMoE.

cs.LG↗

arXiv2025

Can AI Prompt Humans? Multimodal Agents Prompt Players' Game Actions and Show Consequences to Raise Sustainability Awareness

Unsustainable behaviors are challenging to prevent due to their long-term, often unclear consequences. Games offer a promising solution by creating artificial environments where players can immediately experience the outcomes of their actions. To explore this potential, we developed EcoEcho, a GenAI-powered game leveraging multimodal agents to raise sustainability awareness. These agents engage players in natural conversations, prompting them to take in-game actions that lead to visible environmental impacts. We evaluated EcoEcho using a mixed-methods approach with 23 participants. Results show a significant increase in intended sustainable behaviors post-game, although attitudes towards sustainability only slightly improved. This finding highlights the potential of multimodal agents and action-consequence mechanics to effectively motivate real-world behavioral changes such as raising environmental sustainability awareness.

cs.HC↗