HF Daily Papers · 2026-10-27
HF Daily Papers 精选（15 篇，按社区票数排序）
- [224▲] Reading, Writing, Sharing, and Interacting with the World through Video — https://arxiv.org/abs/2610.31668
- [47▲] UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents — https://arxiv.org/abs/2610.30932
- [38▲] HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games — https://arxiv.org/abs/2610.31162
- [34▲] RSIHub: A Composable Framework for Agent-Evolution Methods — https://arxiv.org/abs/2610.32253
- [33▲] RynnUnify: Towards Unified Embodied Brain — https://arxiv.org/abs/2610.32965
- [26▲] Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems — https://arxiv.org/abs/2610.30418
- [24▲] Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models — https://arxiv.org/abs/2610.31198
- [22▲] Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs — https://arxiv.org/abs/2610.27103
- [22▲] EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement? — https://arxiv.org/abs/2610.04184
- [19▲] Every Weight Is a Path of Shared Discrete Decisions — https://arxiv.org/abs/2610.31931
- [19▲] Diffusion Language Models Change Speed Across Tasks and Languages — https://arxiv.org/abs/2610.25835
- [16▲] Dual Exam: Controlled Evaluation of Multimodal Agents and World Models — https://arxiv.org/abs/2610.31066
- [16▲] DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model — https://arxiv.org/abs/2610.31734
- [12▲] TenetBench: A Clause-Anchored Russian Corpus for Evaluating Language Models against Professional Codes of Ethics — https://arxiv.org/abs/2610.29477
- [12▲] On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models — https://arxiv.org/abs/2610.32770