TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
The article introduces TwinRouterBench, a new benchmark for evaluating LLM routing in various applications. It features two tracks: a static track with pre-verified data and a dynamic track for live agent execution. This approach aims to improve cost efficiency while maintaining task success in long-horizon applications.
- ▪TwinRouterBench evaluates LLM routing through a static and a dynamic track.
- ▪The static track includes 970 router-visible prefixes from 520 instances across multiple benchmarks.
- ▪The dynamic track tests routers on a full suite of cases to measure task resolution and API spending.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.18859 |
| Publication time | Wed, 20 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-20T04:04:59.484Z |
| Last seen | 2026-05-20T04:04:59.484Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | dwhkKJcfYmul |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.18859 (cs) [Submitted on 14 May 2026] Title:TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing Authors:Pei Yang, Wanyi Chen, Tongyun Yang, Pengbin Feng, Jiarong Xing, Wentao Guo, Yuhang Yao, Yuhang Han, Hanchen Li, Xu Wang, Zeyu Wang, Jie Xiao, Anjie Yang, Liang Tian, Lynn Ai, Eric Yang, Tianyu Shi View a PDF of the paper titled TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing, by Pei Yang and 16 other authors View PDF HTML (experimental) Abstract:LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many model calls.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
