…Research on the application of RMs in code generation , however, has been comparatively sparse, with existing work largely focusing on execution feedback. This choice constrains post-training to optimizing functional correctness over…
…AI-generated summary We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruction) in a single framework…
…This shift creates safety risks that are difficult to detect from isolated prompts or final responses, because harm often emerges only through multi-step execution traces whose individual actions appear locally benign…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI…
…Jie Zhu , , , , , , , Abstract ESC-Skills is a skill-centric framework that discovers and self-evolves executable emotional support skills through intervention units and multi-profile refinement to improve interpretability and dialogue outcomes…
…For grading, Claw-Eval-Live records execution traces , audit logs , service state, and post-run workspace artifacts, using deterministic checks when evidence is sufficient and structured LLM judging only for semantic dimensions…
…Yipeng Gao , , , , , , , Abstract Vision-language models are evaluated for procedural 3D modeling tasks through a benchmark and ranking platform that assess their ability to translate text and images into executable 3D code…
…However, a significant gap remains between the high-level semantic focus of standard text-guided pre-training paradigms and the low-level spatial and physical knowledge critical for execution in embodied environments…
…Zhengyang Tang , , , , , , , , , , , , , , , , Shangpin Peng , Zheng Ruan , , , , Abstract PhoneWorld is a pipeline that transforms real GUI trajectories and screenshots into controllable mobile environments, executable tasks, and automated verifiers, enabling scalable creation of phone…
…Learning Policies by Repairing Executable Knowledge Bases (2026) Exploring Autonomous Agentic Data Engineering for Model Specialization (2026) Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents (2026) SkillOpt: Executive…