SkillDuet: Co-Evolving Models and Skills through Response Feedback
cs.AI, cs.LG
Submitted: 2026-11-09
Updated: 2026-11-12
Terminology
Sources
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams
- SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- Dynamic Dual-Granularity Skill Bank for Agentic RL
- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
- Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
- OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation
- UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
- ATOD: Annealed Turn-Aware On-Policy Distillation for Multi-Turn Agentic Tasks
- Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
- Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning
- UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
- Proximal Policy Optimization Algorithms
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distilled Agentic Reinforcement Learning
- ICRL: Learning to Internalize Self-Critique with Reinforcement Learning
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