arXiv
Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw
Users increasingly delegate work to autonomous AI agents, yet evaluations typically measure task completion rather th...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-s...
arXiv
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design
Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many i...
HuggingFace
Learning Foresight without Explicit Trajectories for 3D Diffusion Policies
3D diffusion policies are strong at generating geometrically grounded actions from current observations, but successf...
HuggingFace
When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation
Large language models (LLMs) increasingly participate in scientific evaluation, both as automated reviewers and as as...
HuggingFace
MintAct: A Unified Visual Agent for Digital Environments
We present MintAct, a family of vision-language models that unifies UI grounding, multi-step navigation across mobile...
HuggingFace
OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation
Reference-to-video (R2V) generation is evolving toward increasingly general and versatile reference control, giving r...
HuggingFace
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development thr...
HuggingFace
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Reusable skills give agents transferable procedural knowledge, making scalable acquisition essential for extending ag...
HuggingFace
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills
Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidanc...
HuggingFace
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-s...
HuggingFace
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databa...