Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evalua

arXiv:2609.05824v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is

arXiv:2605.11603v1 Announce Type: new Abstract: The growing deployment of large language models (LLMs) makes per-request routing essential for balancing response quality and

arXiv:2609.29109v1 Announce Type: new Abstract: Reasoning-capable language models often produce long chains of thought when direct answers suffice, wasting inference compute. Many

arXiv:2608.18852v1 Announce Type: new Abstract: Agent frameworks increasingly package procedural knowledge as skills: instruction files an agent reads on demand, while public

arXiv:2604.00421v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely

arXiv:2604.00050v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a promising technique for training language models on distributed and private datasets of

arXiv:2609.29154v1 Announce Type: new Abstract: Large language model agents increasingly rely on natural-language skills to solve complex tool-use tasks. However, such tasks often