📄 Paper Explainer

All Explained Papers

4377 papers explained. Page 2 of 219. ← Back to home

• arXiv:2610.37405 · explained 2026-10-30
  Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers
• arXiv:2610.35486 · explained 2026-10-30
  ShutdownMod: Turning Any Trajectory into a Shutdown Evaluation
• arXiv:2610.37631 · explained 2026-10-30
  What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models
• arXiv:2610.37121 · explained 2026-10-30
  Prospector: learning a compact graph traversal policy for scientific reasoning
• arXiv:2610.37342 · explained 2026-10-29
  Aligning Institutional Power and Operational Ability
• arXiv:2610.35586 · explained 2026-10-29
  Linear Probes Transfer from Base to Distilled Language Models despite Rotation
• arXiv:2610.35847 · explained 2026-10-29
  Patient-specific rubric-based evaluation of large language models across longitudinal cancer care
• arXiv:2610.35865 · explained 2026-10-29
  Center-of-Mass Interpretation of Evolution Strategies
• arXiv:2610.35773 · explained 2026-10-29
  A Unified Arena for LLM Agents across Diverse Eurogame
• arXiv:2610.35868 · explained 2026-10-29
  Retriever-Free Retrieval: Navigating Documents with Decision Models
• arXiv:2610.35690 · explained 2026-10-29
  EvoRouter: Cost-Efficient Multi-Agent Routing via Insight-Guided On-Policy Distillation
• arXiv:2610.37624 · explained 2026-10-29
  Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions
• arXiv:2610.37422 · explained 2026-10-29
  Beyond the Readout: A Latent Numerical Frame Shared Across Modality and Operation
• arXiv:2610.37375 · explained 2026-10-29
  Agent-Conditioned Routing: Diverse Reasoning Paths Within One Frozen Model
• arXiv:2610.35753 · explained 2026-10-27
  CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection
• arXiv:2610.31239 · explained 2026-10-25
  Reward-Weighted Preference Optimization for Selective Combinatorial Optimization Problems
• arXiv:2507.10524 · explained 2026-10-25
  Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
• arXiv:2610.28601 · explained 2026-10-23
  Evolving Agent Interfaces
• arXiv:2610.26524 · explained 2026-10-23
  Beyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor Simulation
• arXiv:2610.26679 · explained 2026-10-23
  StebBench: Diagnosing Real-World Procedural Understanding in AI Agents