SkillFM: Generating Skills for LLM Agents via Latent Flow Matching
Quick summary
arXiv:2609.39382v1 Announce Type: new Abstract: Textual skills provide reusable guidance for large language model agents, but existing approaches often rely on manually curated skill banks or reinforcement learning with indirect and delayed feedback. We introduce SkillFM (Skill Flow Matching), a generative framework that synthesizes task-conditioned textual skills directly without test-time skill retrieval. Our framework combines a codec for encoding and reconstructing textual skills in a continuous latent space with a conditional flow model trained using improved MeanFlow. At inference time,
Key takeaways
- arXiv:2609.39382v1 Announce Type: new Abstract: Textual skills provide reusable guidance for large language model agents, but existing approaches often rely on manually curated skill banks or reinforcement learning with indirect and delayed feedback.
- We introduce SkillFM (Skill Flow Matching), a generative framework that synthesizes task-conditioned textual skills directly without test-time skill retrieval.
- Our framework combines a codec for encoding and reconstructing textual skills in a continuous latent space with a conditional flow model trained using improved MeanFlow.
Why it matters
“SkillFM: Generating Skills for LLM Agents via Latent Flow Matching” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments