SkillFM: Generating Skills for LLM Agents via Latent Flow Matching
cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/lulushang999/SkillFM
Terminology
Sources
- Text-to-LoRA: Instant Transformer Adaption
- LLM Latent Reasoning as Chain of Superposition
- Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
- Mean Flows for One-step Generative Modeling
- Improved Mean Flows: On the Challenges of Fastforward Generative Models
- Field-Aware Agent Skill Retrieval
- A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
- Training Large Language Models to Reason in a Continuous Latent Space
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs
- Flow Matching for Generative Modeling
- SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
- SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
- SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
- Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- Scalable Diffusion Models with Transformers
- More Skills, Worse Agents? Skill Shadowing Degrades Performance When Expanding Skill Libraries
- Dynamic Dual-Granularity Skill Bank for Agentic RL
- Voyager: An Open-Ended Embodied Agent with Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems