AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security Paper • 2601.18491 • Published Jan 26 • 125
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents Paper • 2601.16746 • Published Jan 23 • 91
Scaling Embeddings Outperforms Scaling Experts in Language Models Paper • 2601.21204 • Published Jan 29 • 102
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling Paper • 2512.23959 • Published Dec 30, 2025 • 111