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

Indonesian

Sistem AI Conversational Code dibangun pada Data Large Language Models (LLMs) membutuhkan mekanisme routing yang menyeimbangkan kualitas jawaban dan latensi tanggapan pada skala. Namun, referensi routing LLM yang ada mengasumsikan observabilitas penuh dari semua hasil model kandidat, menekankan latensi sebagai metrik kelas pertama, dan penilaian fragmen di seluruh protokol heterogen yang tidak seimbang dengan pengaturan dunia nyata. Kami memperkenalkan RouterWorld, referensi komprehensif untuk routing LLM dalam GenAI konversial. RouterWorld menyatukan 371k tanggapan tanggapan tunggal dan 76k lintasan agen multi tanggapan, mengadopsi interaksi pengguna alami dengan protokol LLM-as-a-judge standar, dan mengecualikan efisiensi publik dari harga transisi melalui pengumuman latensi berbasis perangkat keras

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

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