ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and Stabilize

arXiv:2609.04197 · cs.CL, cs.AI · Submitted 2026-09-03 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-03

Updated: 2026-09-03

Comments: EMNLP 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 43× in this paper · explained in 1 episode
• Benchmark — 24× in this paper · explained in 2 episodes
• Ablation — 21× in this paper · explained in 1 episode
• Generalization — 14× in this paper · explained in 13 episodes
• Clustering — 9× in this paper · explained in 2 episodes
• Error-Structured Prompt Optimization — 6× in this paper
• Commentary — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• Generalization Bounds — 2× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• In International Conference on Machine Learning — 1× in this paper
• Multi-hop Reasoning — 1× in this paper · explained in 3 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• A Toolbox for Improving Evolutionary Prompt Search
• MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization
• Generalizable Self-Evolving Memory for Automatic Prompt Optimization
• Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors
• Automatic Prompt Optimization with "Gradient Descent" and Beam Search
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution
• Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
• TextGrad: Automatic "Differentiation" via Text
• promptolution: A Unified, Modular Framework for Prompt Optimization
• ReflectivePrompt: Reflective evolution in autoprompting algorithms

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering