20 results for “design tasks”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
pcbGPT is a grounded system that automatically generates editable KiCad PCB schematics from natural language requirements, achieving high accuracy on complex embedded design tasks.
This paper introduces ContractHIL-HLS, a contract-aligned multi-agent workflow for practical high-level synthesis engineering, which includes a structured contract, hardware information feedback, and…
The paper assembles a corpus of 102 papers on edge bundling and derives a task taxonomy for reasoning about bundled visualizations.
Peter Kulits, Yiqing Xu, R. Kenny Jones, Cordelia Schmid +1 more
A benchmark for evaluating text-conditioned LEGO-set design agents that can produce physically buildable designs.
Zhiheng Fu, Yupeng Hu, Zixu Li, Zhiwei Chen +6 more
The paper proposes TaskBridge, a framework for reformulating task-oriented queries into product retrieval expressions.
This paper introduces DRAFT-Bench, a lifecycle-oriented evaluation framework for assessing the capabilities of frontier general-purpose agents in design tasks.
A new framework, CAPED, is introduced to characterize user skills required for chart authoring.
Tomer Keren, Nitay Calderon, Asaf Yehudai, Yotam Perlitz +2 more
The paper introduces TASTE, an automatic task synthesis method that generates challenging agent benchmarks by evolving tool sequences, demonstrating that existing benchmarks are saturated and that TAS…
This paper discusses the misalignment between current AI goals and the needs of creators in fields like structural design, and proposes a conversational, multimodal, and responsive AI system for const…
Sizhong Qin, Yi Gu, Yao Jiang, Ao Cai +12 more
This paper introduces StructureClaw, an artifact-centered workbench for evaluating structural-engineering agents, and presents StructureClaw-Bench, an executable benchmark for testing these agents.
Sina Mavali, David Pape, Jonathan Evertz, Samira Abedini +4 more
The paper introduces the Task Alignment Benchmark (TAB) to evaluate terminal agents' ability to selectively follow relevant environmental instructions while ignoring misleading distractors, revealing…
This paper argues that AI in design ideation should be thought of as a friction agent for reflection instead of a smoothing agent for output.
This study investigated the stability and prompt-responsiveness of AI tools in classifying the cognitive demand of math tasks, finding that few-shot prompting was a more reliable performance booster t…
Likai Wang, Dezhao Su, Jing Hu, Yunyun Wan +2 more
A framework for measuring human contributions in human-agent joint production is proposed.
Wenqian Zhang, Yangyi Huang, Zigeng Xu, Weiyang Liu +1 more
The paper proposes a framework, FunCAD-Harness, to improve functional CAD design by translating abstract requirements into physical tests and guiding design revisions.
The paper introduces MUSE, a comprehensive benchmark that evaluates Text-to-CAD generation by assessing complex assemblies based on functionality, manufacturability, and assemblability, moving beyond…
Weihuang Zheng, Tianyuan Zou, Eileen Ye, Alphet Liu +4 more
The paper introduces E-Bench, a synthetic benchmark for evaluating multi-step tool use in Large Language Models across three product domains.
This paper introduces the Goal-Oriented Dialogue Runtime (GODR), a framework-neutral design pattern for managing complex, multi-domain, interruptible conversations with multiple interdependent objecti…