13 papers
LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
Yukang Feng, Jianwen Sun, Zelai Yang +16
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task ho…
World Craft: Agentic Framework to Create Visualizable Worlds via Text
Jianwen Sun, Yukang Feng, Kaining Ying +8
Large Language Models (LLMs) motivate generative agent simulation (e.g., AI Town) to create a ``dynamic world'', holding immense value across entertainment and research. However, f…
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences
Zizhen Li, Chuanhao Li, Yibin Wang +7
Recent advancements have expanded the role of Large Language Models in board games from playing agents to creative co-designers. However, a critical gap remains: current systems la…
ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments
Jiaxin Ai, Yukang Feng, Fanrui Zhang +8
Multimodal agents are making rapid progress on general computer-use tasks, yet existing benchmarks remain largely confined to browsers and basic desktop applications, falling short…
From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration
Jianwen Sun, Fanrui Zhang, Yukang Feng +6
Scientific illustrations demand both high information density and post-editability. However, current generative models have two major limitations: Frist, image generation models ou…
Closing the Expression Gap in LLM Instructions via Socratic Questioning
Jianwen Sun, Yukang Feng, Yifan Chang +6
A fundamental bottleneck in human-AI collaboration is the ``intention expression gap," the difficulty for humans to effectively convey complex, high-dimensional thoughts to AI. Thi…