Model Detail
Auto Router
—Auto Router is a multimodal model released by Openrouter. And supports text+image+file+audio+video->text+image inputs.
Auto Router is priced at $0/M input tokens and $0/M output tokens. Operationally the model offers a 2000K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. At this input rate the model sits in the commodity tier and is suitable for high-volume workloads where per-call cost dominates the decision.
Auto Router is published on Hugging Face but our pipeline has not yet captured architecture, license, or parameter-count metadata for this entry. The data is refreshed daily, so these fields typically populate within 24–48 hours of release.
Auto Router is best fit for mixed text-and-image reasoning tasks such as document understanding, high-volume batch jobs where per-call cost dominates the budget, and long-context tasks such as full-codebase analysis or book-length summarization (2000K tokens). Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
AgentFactory: Towards Automated Agentic System Design and Optimization
arXiv:2609.01045v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and complex task execution. However, current approaches to manually designing and optimizing agentic syst
Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks
arXiv:2609.00763v1 Announce Type: new Abstract: Hierarchical Knowledge graph (KG)-based retrieval augmented generation (RAG) has emerged as a powerful approach for supporting large language models with structured knowledge. However, there are primary challenges: (i) the lack of methods for automatic
Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive Diagnosis
arXiv:2609.01537v1 Announce Type: new Abstract: Q-matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires. Data-driven Q-matrix estimation remains challenging when assessments involve many correlated skill
Does task decomposition improve automatic NLG evaluation?
arXiv:2609.01139v1 Announce Type: new Abstract: The LLM-as-a-judge (LLMaJ) framework has emerged as a promising solution for cheap, reproducible, reference-free Natural Language Generation (NLG) evaluation. Prior work seeks to improve LLMaJ by decomposing evaluation tasks into simpler sub-tasks. In
KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training
arXiv:2609.00082v1 Announce Type: cross Abstract: LLMs acquire vast amounts of knowledge during pre-training, but often lack the specialized knowledge needed to answer questions from niche sources such as manuals or technical documents unseen during pre-training. Continued pre-training (CPT) is wide
LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Results and Implications From A New Benchmark
arXiv:2609.00192v1 Announce Type: new Abstract: Public trust in Autonomous Vehicles (AVs) may depend not only on technical success but also on the fairness of their decision making. While a recent trend in AV research involves using general purpose "common sense" models to guide AV decision making,
