MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution
cs.CL
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
- Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning
- SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment
- Self-Distilled Agentic Reinforcement Learning
- SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
- Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
- Dynamic Dual-Granularity Skill Bank for Agentic RL
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data