arXiv subjects

Xiaoke Yan

Publications and source records attributed to Xiaoke Yan.

3 recordsLinked to original sources

arXiv2026

From Watching to Steering: Enabling Human-Coding Agent Collaboration through Execution Traces

Recent advances in large language models (LLMs) have enabled coding agents to autonomously perform complex software development tasks, yet their long-running execution remains difficult for users to inspect, understand, and steer. We present Vibetrace, an interactive trace visualization and intervention system for agentic programming built upon OpenCode. Vibetrace introduces a human-agent collaboration paradigm of Observe, Understand, Intervene, and Evolve. It (1) visualizes agent workflows as interactive execution traces for inspecting actions, intermediate states, and failures; (2) enables users to fork execution from prior steps and provide targeted corrections without restarting validated progress; and (3) distills traces and human feedback into reusable skills for continual agent evolution. On SWE-bench Verified, distilled skills reduce input tokens by 23.0% and cost by 15.5%, while improving pass rate from 65.0% to 68.0%. User studies further demonstrate improved accuracy and efficiency over conventional log-based interaction.

cs.HC↗

arXiv2025

CODS : A Theoretical Model for Computational Design Based on Design Space

We introduce CODS (Computational Optimization in Design Space), a theoretical model that frames computational design as a constrained optimization problem over a structured, multi-dimensional design space. Unlike existing methods that rely on handcrafted heuristics or domain-specific rules, CODS provides a generalizable and interpretable framework that supports diverse design tasks. Given a user requirement and a well-defined design space, CODS automatically derives soft and hard constraints using large language models through a structured prompt engineering pipeline. These constraints guide the optimization process to generate design solutions that are coherent, expressive, and aligned with user intent. We validate our approach across two domains-visualization design and knitwear generation-demonstrating superior performance in design quality, intent alignment, and user preference compared to existing LLM-based methods. CODS offers a unified foundation for scalable, controllable, and AI-powered design automation.

cs.HC↗

arXiv2025

IDEA: Augmenting Design Intelligence through Design Space Exploration

Design spaces serve as a conceptual framework that enables designers to explore feasible solutions through the selection and combination of design elements. However, effective decision-making remains heavily dependent on the designer's experience, and the absence of mathematical formalization prevents computational support for automated design processes. To bridge this gap, we introduce a structured representation that models design spaces with orthogonal dimensions and discrete selectable elements. Building on this model, we present IDEA, a decision-making framework for augmenting design intelligence through design space exploration to generate effective outcomes. Specifically, IDEA leverages large language models (LLMs) for constraint generation, incorporates a Monte Carlo Tree Search (MCTS) algorithm guided by these constraints to explore the design space efficiently, and instantiates abstract decisions into domain-specific implementations. We validate IDEA in two design scenarios: data-driven article composition and pictorial visualization generation, supported by example results, expert interviews, and a user study. The evaluation demonstrates the IDEA's adaptability across domains and its capability to produce superior design outcomes.

cs.HC↗