Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
- Qwen3 Technical Report
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
- SkillEvolver: Skill Learning as a Meta-Skill
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
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