InferenceDynamics: Adaptive LLM Routing through Structured Capability and Knowledge Profiling

ACL ARR 2026 January Submission8793 Authors

Keywords: efficient models, domain adaptation, inference methods, interactive and collaborative generation

Abstract: Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs, enabling the selection of the best-performing LLMs for specific user queries while balancing performance and cost. However, current routing approaches often face limitations in scalability when dealing with a large pool of specialized LLMs, or in their adaptability to extending model scope and evolving capability domains. To overcome those challenges, we propose **InferenceDynamics**, a flexible and scalable multi-dimensional routing framework by modeling the capability and knowledge of models. We operate it on our comprehensive dataset **RouteMix**, and demonstrate its effectiveness and generalizability in group-level routing using modern benchmarks including MMLU-Pro, GPQA, BigGenBench, and LiveBench, showcasing its ability to identify and leverage top-performing models for given tasks, leading to superior outcomes with cost efficiency. The broader adoption of InferenceDynamics can empower users to harness the full specialized potential of the LLM ecosystem, and our code will be made publicly available to encourage further research.

Paper Type: Long

Research Area: Natural Language Generation

Research Area Keywords: efficient models, domain adaptation, inference methods, interactive and collaborative generation

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English

Submission Number: 8793