Verification and Self-Improvement in Agentic AI: Foundations and Limits
cs.AI, cs.CC
Submitted: 2026-10-07
Updated: 2026-10-07
Terminology
Sources
- The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
- AI safety via debate
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
- Large Language Models Cannot Self-Correct Reasoning Yet
- Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
- Recursive self-improvement of AI research agents
- RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
- Preserving Statistical Validity in Adaptive Data Analysis
- Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
- Hyperagents
- Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- AFlow: Automating Agentic Workflow Generation
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- Self Improvement via Fast Tree-search
- Self-Harness: Harnesses That Improve Themselves
- Why Do Multi-Agent LLM Systems Fail?
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