The paper demonstrates that in open‑weight LLM inference markets, selecting a model is insufficient; clients must also choose a provider, as the same model can differ markedly in quality, latency, availability, and price across providers. The authors propose a market‑aware routing approach, including a measured‑map policy and an online router called FACET, which certifies provider feasibility for each task and safely falls back to a reliable anchor. Experiments show that this strategy yields cost savings while maintaining quality and avoiding degraded endpoints.
arXiv:2605.18859v3 Announce Type: replace-cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single u...
arXiv:2609.28322v1 Announce Type: new Abstract: Benchmarking and routing platforms increasingly act as intermediaries connecting large language model providers with end-users. However, providers on t...
arXiv:2607. 08665v1 Announce Type: new Abstract: Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle.
HybridInfer is a thermal‑aware reinforcement‑learning router that selects among on‑device, edge, and cloud large language model tiers based on a phone’s thermal headroom and query complexity. Trained offline with a Q‑learning policy, it balances quality, latency, cost, and a thermal penalty, and includes a locality bonus that encourages on‑device execution. In real Android tests on 210 prompts, the learned router outperformed two hand‑tuned heuristics in quality while maintaining the lowest cost, and it proved more reliable and faster than always‑on‑device inference, especially for long queries.
arXiv:2608. 20316v1 Announce Type: new Abstract: Heterogeneous AI systems composed of multiple models, architectures, harnesses, or inference-time settings can improve quality and efficiency by routing queries to the specialist who can answer most effectively at the lowest cost.
arXiv:2607. 27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental tool-selection challenge: acquiring too few tools leaves the task under-informed, while too many adds cost, context load, and privacy exposure.
arXiv:2606. 18774v1 Announce Type: new Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://routejudge.
arXiv:2606. 19376v1 Announce Type: cross Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost.
arXiv:2608. 12719v1 Announce Type: cross Abstract: Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center to predict model performance, creating an information-risk mismatch and a scalability bottleneck as the model pool grows.
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.
PriceBench is a diagnostic benchmark that extracts price, quality, and brand preferences from large language models (LLMs) by analyzing their hotel booking choices. Using a logit choice model, the study evaluated 28 LLMs from eight providers across 3,600 booking tasks involving 179 New York City hotels. Results show that more capable LLMs exhibit stronger, more consistent preferences, while weaker models either lock onto a single position or show near-indifference, with significant variation in price sensitivity and price/quality trade-offs across providers.
arXiv:2606. 02581v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and end-to-end latency.