10 papers
MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning
Hanye Zhao, Muning Wen, Yong Yu +1
Allocating limited computation among concurrent learning tasks is difficult when each task must reach a target loss before a deadline but its required training effort is unknown. E…
SW--Bench: Benchmarking Autonomous Software Agent Generation for Agentic Web
Linyao Chen, Bo Huang, Qinlao Zhao +13
The Agentic Web is emerging as a paradigm in which autonomous software agents interact with online resources and with each other to accomplish user goals. However, the capacity of…
DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning
Hanye Zhao, Xiaoshen Han, Zhengbang Zhu +4
With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential in decision-making and control. M…
UniCon: A Unified System for Efficient Robot Learning Transfers
Yunfeng Lin, Li Xu, Yong Yu +2
Deploying learning-based controllers across heterogeneous robots is challenging due to platform differences, inconsistent interfaces, and inefficient middleware. To address these i…
H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer
Yunfeng Lin, Minghuan Liu, Yufei Xue +4
The rapid advancement of humanoid robotics has intensified the need for robust and adaptable controllers to enable stable and efficient locomotion across diverse platforms. However…
Understanding and Optimizing Agentic Workflows via Shapley value
Yingxuan Yang, Bo Huang, Siyuan Qi +14
Agentic workflows have become the dominant paradigm for building complex AI systems, orchestrating specialized components, such as planning, reasoning, action execution, and reflec…