From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement
cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/Prism-Shadow/awesome-rsi
Project page: https://prism-shadow.github.io/awesome-rsi
Sources
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- SkillAdam: Stable and Efficient Skill Evolution for Agents
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
- Self-Refine: Iterative Refinement with Self-Feedback
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- Hyperagents
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- A-MEM: Agentic Memory for LLM Agents
- TTSE: A Two-Track Online Self-Evolution Framework
- SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction
- Knowledge-Centric Self-Improvement
- TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
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
- Agents' Last Exam
- 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