Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback
cs.CL
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion
- LongLaMP: A Benchmark for Personalized Long-form Text Generation
- MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
- Text as a Universal Interface for Transferable Personalization
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- RLVF: Learning from Verbal Feedback without Overgeneralization
- From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents
- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- Agent Workflow Memory
- Qwen3 Technical Report
- Qwen2.5 Technical Report
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
- Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering