arXiv
Argus: A General-Purpose Agentic Runtime for Long-Horizon Reasoning
Long-horizon reasoning requires an agentic runtime that can persist when evidence supports its current approach and p...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
UniWorld-View: Large-Baseline View Synthesis via Video Diffusion Models
The abundance of casually captured monocular videos and images on social media provides a valuable source for immersi...
HuggingFace
SKILL-KD: Contrastive Skill Distillation for LLM Agents
Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing ...
HuggingFace
NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap
We introduce NOLLI, a procedurally generated English-Korean puzzle benchmark designed to diagnose where Korean perfor...
HuggingFace
When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents
Memory-augmented VLM agents act on persistent spatial knowledge, yet that knowledge silently goes stale as the enviro...
HuggingFace
Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain,...
HuggingFace
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
Personalized LLMs with persistent memory are increasingly deployed, yet the faithfulness of their user models remains...
HuggingFace
When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation
On-Policy distillation (OPD) transfers teacher capabilities by supervising student-sampled trajectories with dense to...
HuggingFace
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are ...
HuggingFace
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
Interactive video world models are essential for long-horizon planning and exploration, yet they suffer from compound...
HuggingFace
BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation
Leveraging pre-trained vision-language models (VLMs) to construct vision-language-action (VLA) models has emerged as ...
HuggingFace
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language...