arXiv AI
The Router Within: Eliciting Native Skill Routing from a Frozen LLM
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 21
SkillRouter: Skill Routing for LLM Agents at Scale
arXiv:2603. 22455v5 Announce Type: replace Abstract: Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks.
arXiv AI
Sep 30
SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
SkillGym is an automatic pipeline that generates verifiable environments for training skill-use agents. It crawls internet skills, filters for reproducible workflows, and uses a builder‑reviewer process to create difficulty‑controlled tasks with reference solutions and verifiers. The system builds 6.8k environments, collects 19k successful trajectories, and fine‑tunes LLMs from 2B to 122B parameters, improving performance and skill invocation rates.
arXiv AI
Sep 1
SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
arXiv:2605.05726v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical...
arXiv AI
Oct 1
SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale
arXiv:2609.38822v1 Announce Type: cross Abstract: Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown pas...
arXiv AI
Sep 28
SkillFlow: Scalable and Efficient Agent Skill Retrieval System
SkillFlow is an open, multi-stage retrieval system that helps AI agents selectively load relevant skills from a large library of community-contributed SKILL.md definitions. The pipeline uses dense retrieval, two rounds of cross-encoder reranking, and LLM-based selection to balance recall and precision. Evaluations on SkillsBench and Terminal-Bench show that SkillFlow improves performance when high-quality skills are available, but retrieval alone does not help if the corpus lacks executable skills for the target domain.
arXiv Machine Learning
3d ago
TalentRL: Strategy-Guided Reinforcement Learning for Hierarchical Skill Routing
TalentRL is a strategy‑guided reinforcement learning framework that routes natural‑language skills hierarchically, using coarse‑grained talents to guide fine‑grained skill retrieval. The method trains talent routing via reward contrasts and optimizes execution with group‑relative advantages, achieving significant performance gains on open‑domain QA benchmarks and agentic tasks such as ALFWorld and WebShop.