SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
cs.LG
Submitted: 2026-02-09
Updated: 2026-10-07
Comments: NeurIPS 2026
Code: https://github.com/aiming-lab/SkillRL
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen Technical Report
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Memp: Exploring Agent Procedural Memory
- Group-in-Group Policy Optimization for LLM Agent Training
- A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Memory in the Age of AI Agents
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning
- SimpleMem: Efficient Lifelong Memory for LLM Agents
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ZeroSearch: Incentivize the Search Capability of LLMs without Searching
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
- Kimi K2.5: Visual Agentic Intelligence
- Tongyi DeepResearch Technical Report
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks