R squared Flow: Recursive Self-Improvement via Recursive Skill Evolution
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/beita6969/r2flow
Terminology
Sources
- HealthBench: Evaluating Large Language Models Towards Improved Human Health
- Program Synthesis with Large Language Models
- SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
- SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
- $f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
- SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
- Measuring Mathematical Problem Solving With the MATH Dataset
- GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
- Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries
- Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
- MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
- Agents that Matter: How Subtle Choices Shape Agent Attribution in Multi-Agent Systems
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- SkillOS: Learning Skill Curation for Self-Evolving Agents
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Self-Improvements in Modern Agentic Systems: A Survey
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Related papers
- 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
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection