arXiv AI
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 18
Task- and Session-Level Model Routing: A Common-Interface Hybrid Evaluation of Four Open-Source Routers Across Four Benchmarks
arXiv:2608. 14641v1 Announce Type: new Abstract: Agentic systems increasingly delegate model selection to a router, yet open-source routers are usually evaluated with different tasks, candidate pools, and execution protocols, limiting direct comparison.
arXiv AI
Jul 14
Agentic Routing: The Harness-Native Data Flywheel
arXiv:2607. 11399v1 Announce Type: cross Abstract: Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification.
arXiv Machine Learning
Jul 27
TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI
arXiv:2607. 22465v1 Announce Type: cross Abstract: Routing to select large language models (LLMs) with different cost-quality trade-offs has become a fundamental deployment feature of enterprise AI.
arXiv AI
Jun 29
Agent-as-a-Router: Agentic Model Routing for Coding Tasks
arXiv:2606. 22902v3 Announce Type: replace Abstract: Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct domains, yet none dominate all.
arXiv Machine Learning
Jun 16
HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools
arXiv:2605. 17106v2 Announce Type: replace-cross Abstract: Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences.
arXiv Machine Learning
Aug 4
MetaRoute-Bench: Evaluating Meta-Decision Policies for Agentic Workflow Routing
arXiv:2608. 00107v1 Announce Type: new Abstract: Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an intermediate result, or recover from failure.