SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration
cs.CL
Submitted: 2026-06-17
Updated: 2026-11-03
Code: https://github.com/slingshot-ai/sage
Terminology
Sources
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- DeepSeek-V3 Technical Report
- MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
- A Survey of Context Engineering for Large Language Models
- Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization
- FiNER-ORD: Financial Named Entity Recognition Open Research Dataset
- Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue
- Engagement Phenotypes for a Sample of 102,684 AI Mental Health Chatbot Users and Dose-Response Associations with Clinical Outcomes
- Meta Context Engineering via Agentic Skill Evolution
- TextGrad: Automatic "Differentiation" via Text
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data