Agents Score 58.1%, but Only 2.8% Pass Every Test

Featured

• RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents score 10
  入选 HF Daily Papers; HF 热度: 25 upvotes (+4); 有代码实现; 关键词(2): coding, open-source
• CodeMidas: Scaling Agentic Coding RL Environments from Code Itself score 8
  入选 HF Daily Papers; HF 热度: 21 upvotes (+4); 关键词(5): scaling, GRPO, agentic, coding, open-source
• GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills score 6
  入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 有代码实现

Also Worth Noting

• MintAct: A Unified Visual Agent for Digital Environments score 4
  入选 HF Daily Papers; 关键词(3): serving, tool use, vision-language
• When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Traces score 4
  关键词(1): reasoning; 顶会接收: EMNLP
• PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR score 4
  关键词(1): open-source; 顶会接收: EMNLP
• CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation score 4
  机构: Alibaba; 关键词(1): text-to-video
• GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation score 4
  关键词(2): distillation, reasoning; 顶会接收: EMNLP
• PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object Detection score 4
  关键词(3): quantization, latency, mamba; 顶会接收: ECCV
• Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts score 4
  关键词(1): lightweight; 顶会接收: EMNLP
• OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation score 3
  入选 HF Daily Papers
• Cube-Splat: High-Fidelity 360° Gaussian Splatting SLAM via Cubemap Factorization and Adjoint-Consistent Optimization score 3
  顶会接收: ECCV
• From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers score 3
  顶会接收: EMNLP