HF Daily Papers · 2026-10-20

HF Daily Papers 精选（15 篇，按社区票数排序）

  • [144▲] Learning to Think and Explore in 3D World — https://arxiv.org/abs/2610.21783
  • [111▲] LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets — https://arxiv.org/abs/2610.09872
  • [75▲] LEV: Thinking Fast and Deep with Looped Decision Models — https://arxiv.org/abs/2610.20951
  • [49▲] Scene-Designer: Learning Design Intelligence for Agentic 3D Scene Generation — https://arxiv.org/abs/2610.23121
  • [39▲] OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools — https://arxiv.org/abs/2610.14157
  • [36▲] From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research — https://arxiv.org/abs/2610.21767
  • [35▲] BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries — https://arxiv.org/abs/2610.14746
  • [32▲] Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics — https://arxiv.org/abs/2610.22169
  • [31▲] PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews — https://arxiv.org/abs/2610.21046
  • [26▲] Xiaomi-Lens-0 Technical Report — https://arxiv.org/abs/2610.23279
  • [23▲] RAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted Exemplars — https://arxiv.org/abs/2610.23230
  • [22▲] Execution Before Memory: Diagnosing Memory Failures in Video World Models — https://arxiv.org/abs/2610.23542
  • [17▲] OfficeTown: Generative Organizations for Evolving Agent Intelligence — https://arxiv.org/abs/2610.23194
  • [17▲] Can Visual Generation Expand What Unified Multimodal Models Know? — https://arxiv.org/abs/2610.21459
  • [16▲] MOSS-Image Technical Report — https://arxiv.org/abs/2610.23374