20:13
2026-06-02
vllm.ai
large-language-models
Session-Aware Agentic Routing: Continuity-Aware Model Selection for Long-Horizon
Researchers introduced Session-Aware Agentic Routing (SAAR), a continuity-aware model selection policy for long-horizon LLM agents that adds session memory and safety constraints to vLLM Semantic Routβ¦