How Should a Prompt Optimizer Spend a Tight Budget? BudgetAPO with Noise-Adaptive Evaluation
cs.AI
Submitted: 2026-10-05
Updated: 2026-10-09
Sources
- Instruction Stacking Collapse: A Benchmark and the Capability-Dependent Value of Prompt Compilation
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
- Empirical Bernstein Bounds and Sample Variance Penalization
- tinyBenchmarks: evaluating LLMs with fewer examples
- Generalizing Verifiable Instruction Following
- Gemma 4 Technical Report
- Qwen3 Technical Report
- CAPO: Cost-Aware Prompt Optimization
- GLM-5: from Vibe Coding to Agentic Engineering
- Large Language Models Are Human-Level Prompt Engineers
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