9 papers
Collaborative Learning and Reasoning over Model Slices
Yuheng Wang, Runde Yang, Zhuohan Bao +9
Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite these strengths, single-model re…
CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection
Lin Wu, Shu Yao, Yuheng Wang +11
Training multi-agent collaboration requires trajectories of checking, feedback, and repair, yet task-solving rollouts may end in immediate approval or repeat unsuccessful attempts…
ChatDev 2.0: A No-Code Multi-Agent Platform for Developing Everything
Yufan Dang, Shu Yao, Bowen Lai +6
Large language model (LLM)-based multi-agent systems (MAS) have shown strong potential for solving complex tasks, yet their development forces a tradeoff: code frameworks are expre…
DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments
Huatao Li, Xinwei Geng, Yuheng Wang +9
LLM-based agents have rapidly improved at operating individual digital environments such as mobile applications, desktop systems, and smart homes. However, real-world user goals of…
PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning
Qiran Zhang, Yuheng Wang, Runde Yang +9
Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluating whether language models…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous Science
Jingru Fan, Dewen Liu, Yufan Dang +15
Recent advancements in Large Language Models (LLMs) have greatly extended the capabilities of Multi-Agent Systems (MAS), demonstrating significant effectiveness across a wide range…
AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction
Ruijie Shi, Houbin Zhang, Yuecheng Han +8
Large Language Models have shown strong capabilities in complex problem solving, yet many agentic systems remain difficult to interpret and control due to opaque internal workflows…
TeachMaster: Generative Teaching via Code
Yuheng Wang, Runde Yang, Lin Wu +9
The scalability of high-quality online education is hindered by the high costs and slow cycles of manual content creation. Despite advancements in video generation, current approac…