Newest papers

RouterWorld: Scaling Conversational AI with Latency-Aware LLM Routing

Jinyang Li, Denis Emelin, Simone Tedeschi, Weiwei Cheng, Cristina Morariu, Haytham Assem, Jens Lehmann, Emine Yılmaz, Angus Addlesee · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26511 · cited by 0 works (OpenAlex) · open-access PDF

French

Les systèmes d'IA de codage de conversation basés sur des modèles de données de langue majeure (LLM) nécessitent des mécanismes de routage qui équilibrent la qualité de la réponse et la latence de la réponse à l'échelle. Cependant, les critères de référence de routage LLM existants supposent la pleine observabilité de tous les résultats du modèle candidat, sous-accentuant la latence en tant que métrique de première classe et l'évaluation des fragments sur des protocoles hétérogènes désalignés avec les paramètres du monde réel. Nous introduisons RouterWorld, un critère de référence complet pour le routage LLM dans GenAI de conversation. RouterWorld unifie 371k de réponses à tour unique et 76k de trajecto

Machine translation (Meta M2M100); the English original follows.

Abstract

Conversational AI systems built on Large Language Models (LLMs) require routing mechanisms that balance answer quality and response latency at scale. However, existing LLM routing benchmarks assume full observability of all candidate model outcomes, under-emphasize latency as a first-class metric, and fragment evaluation across heterogeneous protocols misaligned with real-world settings. We introduce RouterWorld, a comprehensive benchmark for LLM routing in conversational GenAI. RouterWorld unifies 371k single-turn responses and 76k multi-turn agentic trajectories, adopts natural user interactions with a standardized LLM-as-a-judge protocol, and decouples efficiency from transient pricing via hardware-grounded latency annotations. Crucially, RouterWorld formalizes routing under partial observability through two setups: Cold-Start, which restricts learning to sparse, static logs, and Voyager, which models continuous data streams where routing decisions shape future training distributions. Evaluating 13 routing baselines, we find that most routers over-emphasize accuracy while ignoring latency under partial observability. Code and benchmark data are publicly available.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Observability, Latency (audio), Static routing, Benchmark (surveying), Link-state routing protocol

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26511, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange