SkillAny: Online Skill Learning for Language Agents at Any Intermediate State
cs.AI
Submitted: 2026-06-03
Updated: 2026-11-07
Code: https://github.com/plusnli/skill-dyn
Terminology
Sources
- GPT-4 Technical Report
- Memp: Exploring Agent Procedural Memory
- XSkill: Continual Learning from Experience and Skills in Multimodal Agents
- MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
- ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
- WebGPT: Browser-assisted question-answering with human feedback
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution
- AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
- RSTR: Reducing SpatioTemporal Redundancy in Diffusion Transformers
- Palette: A Modular and Efficient Framework for On-demand Authorized Safety Relaxation
- Q-realign: Piggybacking Realignment on Quantization for Safe and Efficient LLM Deployment
- SkillX: Automatically Constructing Skill Knowledge Bases for Agents
- SkillOrchestra: Learning to Route Agents via Skill Transfer
- WebXSkill: Skill Learning for Autonomous Web Agents
- Inducing Programmatic Skills for Agentic Tasks
- Qwen3 Technical Report
- Concept-Centric Token Interpretation for Vector-Quantized Generative Models
- Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback
- PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents