Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in domains where task outcomes can be reliably evaluated, but long-horizon interaction remains challenging due to sparse terminal feedback and difficult credit assignment. Process rewards provide denser supervision, yet the capabiliti...
Heng-Bo Xiao, Bo-Yao Zhang, Pu-Rui Liu et al.· 0 citations
Surgical robotic systems are increasingly being adopted as clinical workload rises, motivating autonomous solutions for repetitive manipulation subtasks. Learning-based controllers improve generalization compared with rule-based and analytic approaches, but most are trained for individual tasks and remain difficult to...
Mingwu Su, Guan-Kun Wang, Jinsong Lin et al.· 0 citations
BlueLM-GUI, a 35B-A3B mobile GUI agent built as a real-device-centric flywheel that closes gaps through three principles, demonstrates that grounding model training and iterative improvement in both real devices and the three Every principles yields strong, robust, and transferable mobile GUI capability.
Tong Ye, Kunyang Han, Guo-Zhi Wang et al.· 0 citations
DeepSearch-Evolve is presented, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools that enables scalable self-evolution for long-horizon web agents.
SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and distills their behavioral effect back into the policy model, is proposed.
Jinyang Wu, Shuo Yang, Zhengxi Lu et al.· arXiv.org· 7 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
