Papers

• A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces (2026)
  Mingxuan Du et al.
  1.94
• Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon (2026)
  Víctor Gallego
  1.94
• Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency (2026)
  Anis Radianis
  1.94
• FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search (2026)
  James Xu Zhao et al.
  1.94
• GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs (2026)
  Mohamed Eltahir et al.
  1.89
• Compiler-First State Space Duality and Portable O(1) Autoregressive Caching for Inference (2026)
  Cosmo Santoni
  1.78
• Reasoning over mathematical objects: on-policy reward modeling and test time aggregation (2026)
  Pranjal Aggarwal et al.
  1.78
• Rank1: Test-Time Compute for Reranking in Information Retrieval (2025)
  Orion Weller et al.
  1.28
• Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning (2025)
  Yuxiao Qu et al.
  1.28
• ReasonIR: Training Retrievers for Reasoning Tasks (2025)
  Rulin Shao et al.
  1.28
• Inverse Scaling in Test-Time Compute (2025)
  Aryo Pradipta Gema et al.
  1.28
• Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing (2025)
  Jeffrey Amico et al.
  1.28
• The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute (2025)
  Aman Sharma et al.
  1.28
• Improving Autonomous AI Agents with Reflective Tree Search and Self-Learning (2024)
  Xiao Yu et al.
  —