📄 Paper Explainer

All Explained Papers

4378 papers explained. Page 3 of 219. ← Back to home

• arXiv:2610.26679 · explained 2026-10-23
  StebBench: Diagnosing Real-World Procedural Understanding in AI Agents
• arXiv:2610.26664 · explained 2026-10-23
  Honeypots for AI Agent Insider Threats
• arXiv:2610.26632 · explained 2026-10-23
  When the harness decides success: state that cannot be re-observed
• arXiv:2610.28325 · explained 2026-10-22
  Is Sycophancy a Form of In-Context Updating?
• arXiv:2610.28405 · explained 2026-10-22
  DIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams
• arXiv:2610.26554 · explained 2026-10-22
  BetaMem: Learning to Remember a Changing World for Embodied Agents
• arXiv:2610.28354 · explained 2026-10-22
  S-Agent 2.0: Spatial Reasoning with a General Coding Agent
• arXiv:2610.28568 · explained 2026-10-22
  Evolving Semantic Indexes for Generative Retrieval
• arXiv:2610.28522 · explained 2026-10-22
  DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems
• arXiv:2610.26662 · explained 2026-10-22
  AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous Regimes
• arXiv:2610.28595 · explained 2026-10-22
  What Do RTL Repair Benchmarks Actually Measure?
• arXiv:2610.26650 · explained 2026-10-22
  From Outcomes to Components: A Counterfactual Evaluation Framework for LLM-Proposed Repairs
• arXiv:2610.28385 · explained 2026-10-22
  RACE: RoPE-Aligned Attention Compression Based on Query-Key Activation Energies
• arXiv:2610.28578 · explained 2026-10-22
  Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
• arXiv:2610.28484 · explained 2026-10-22
  Proof-Carrying Contracts: Commitments AI Agents Cannot Break
• arXiv:2610.26829 · explained 2026-10-22
  ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry
• arXiv:2610.26787 · explained 2026-10-21
  LG-Bench: A Graph-Structured Evaluation Benchmark for Life Sciences
• arXiv:2610.26793 · explained 2026-10-21
  SOMA: Continuous Monitoring and Intervention for System Two Reasoning with System One Models
• arXiv:2610.26542 · explained 2026-10-21
  Breaking Diffusion: Parallel Reasoning with Draft Refinement
• arXiv:2610.26528 · explained 2026-10-21
  A Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenes