# Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback

arXiv: https://arxiv.org/abs/2610.19380 · HTML: https://mlsanity.com/paper/2610.19380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution](https://mlsanity.com/paper/2603.01145/) (2026)
- [LongLaMP: A Benchmark for Personalized Long-form Text Generation](https://mlsanity.com/paper/2407.11016/) (2024)
- [LLMs + Persona-Plug = Personalized LLMs](https://mlsanity.com/paper/2409.11901/) (2024)
- [MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation](https://mlsanity.com/paper/2605.27366/) (2026)
- [Preference-Aware Memory Update for Long-Term LLM Agents](https://mlsanity.com/paper/2510.09720/) (2025)
- [RLVF: Learning from Verbal Feedback without Overgeneralization](https://mlsanity.com/paper/2402.10893/) (2024)
- [Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas](https://mlsanity.com/paper/2501.11549/) (2025)
- [PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process](https://mlsanity.com/paper/2507.04607/) (2025)
- [PersonaAgent: Bridging Memory and Action for Personalized LLM Agents](https://mlsanity.com/paper/2506.06254/) (2025)
- [WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution](https://mlsanity.com/paper/2608.27454/) (2026)
- [CoPL: Collaborative Preference Learning for Personalizing LLMs](https://mlsanity.com/paper/2503.01658/) (2025)
- [Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents](https://mlsanity.com/paper/2606.13174/) (2026)
- [From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.16621/) (2026)
- [SkillCommit: Evolving Agent Skills through Behaviorally Validated Scope Expansion](https://mlsanity.com/paper/2608.15165/) (2026)
- [Text as a Universal Interface for Transferable Personalization](https://mlsanity.com/paper/2601.04963/) (2026)

## Abstract (arXiv)

User feedback enables LLMs to refine reusable personalized skills, but often mixes persistent preferences with request-specific corrections. Indiscriminately retaining both risks negative transfer, motivating selective retention at the level of individual requirements. We frame this challenge as selective transfer over atomic rules and propose SkillGrain, a framework for learning reusable personalized skills from user feedback. SkillGrain decomposes feedback into independently actionable rules, predicts their transferability, and retains only those suitable for future requests. To learn these decisions, we combine rubric-guided skill rewards with fine-grained credit assignment that separately evaluates rule content and retention decisions. We further jointly optimize skill induction and skill-conditioned generation through reinforcement learning, ensuring that learned skills support downstream personalization. We construct a benchmark spanning five personalized writing tasks to evaluate cross-request generalization. Experiments across three base models in both in-domain and out-of-domain settings show that SkillGrain achieves the best overall average performance among competing methods.