arXiv AI

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

ESPO (Error-Structured Prompt Optimization) addresses prompt bloat in evolutionary prompt optimizers by splitting the optimization process into Diagnose, Propose, and Select phases. It clusters training errors into structural patterns, generates diverse candidate prompts through four complementary strategies, and applies bootstrap stability selection. Across seven NLP benchmarks, ESPO improves average accuracy by +3.76 pp over GEPA, produces prompts 47 % shorter, and achieves higher accuracy on four additional student models, with the largest gain on Qwen3 GSM8K.

Hugging Face Trending Papers

Sep 3

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

ESPO (Error-Structured Prompt Optimization) addresses prompt bloat in evolutionary prompt optimizers by separating optimization into Diagnose, Propose, and Select phases. It clusters training errors, generates diverse candidates, and applies bootstrap stability selection, achieving a 3.76‑point accuracy gain over GEPA on seven NLP benchmarks while producing 47% shorter prompts. Cross‑model tests on four additional student models confirm ESPO’s superior average accuracy, notably improving Qwen3 GSM8K from 15.00% to 91.40%.

llms nlp benchmarks

arXiv AI

Aug 12

RLMOpt: Adaptive Prompt Optimization via Recursive Language Models

arXiv:2608. 10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization procedure: the algorithm determines which candidates to explore and how the search progresses, while the language model generates or refines prompt proposals.

By Subhash Bangalore Satheesha, Nirvik Pande, Deepthi Duddempudi, Bharath Dandala

llms agents nlp benchmarks

arXiv AI

3d ago

Failure-Guided Co-Evolution of Prompts and Training Data

arXiv:2609.15209v1 Announce Type: cross Abstract: Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data...

By Tianyu Yuan, Zhuzhong Qian

benchmarks

arXiv AI

Jun 19

FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines

arXiv:2606. 19605v1 Announce Type: cross Abstract: Multi-step LLM pipelines fail through interactions among retrieval, reasoning, and formatting steps, so prompt-only optimization can miss bottlenecks in the chain.

By Paul Kassianik, Baturay Saglam, Huaibo Zhao, Blaine Nelson, Supriti Vijay, Aman Priyanshu, Amin Karbasi

llms agents benchmarks

arXiv Machine Learning

Jul 15

MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization

arXiv:2607. 11944v1 Announce Type: cross Abstract: How do different components of iterative prompt optimization interact, and what happens when they are combined?

By Prateek Singh

llms benchmarks

arXiv AI

Jun 29

When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model

arXiv:2606. 21641v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations.

By Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta, Nithish Kumar Prabhakaran

llms benchmarks

arXiv AI

Jul 29

Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization

arXiv:2607. 25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed.

By Zhengtao Yao, Runhao Li, Xupeng Chen, Jiayi Cheng, Chenqian Le, Michael Yue, Siheng Wang, Haoyan Xu, Yuqi Li, Chenhao Wei, Zhengdao Li, Rongchao Zhang, Guang Yang, Yidong Wang, Junhao Dong

llms safety

arXiv AI

Jul 21

OR Else: A Differentiable Trust Region for Policy Optimization

arXiv:2607. 18163v1 Announce Type: cross Abstract: PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable-direction saturation introduces an abrupt change in the scalar objective's derivative.

By Chinmay Rane, Kanishka Tyagi, Michael Manry

llms reinforcement-learning

arXiv Machine Learning

Jul 17

Selecting Hyperparameters for Tree-Boosting

arXiv:2602. 05786v3 Announce Type: replace Abstract: Tree-boosting is a widely used machine learning technique for tabular data.

By Floris Jan Koster, Fabio Sigrist

arXiv AI

Jul 28

Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models

arXiv:2607. 24562v1 Announce Type: new Abstract: Large language models serve heterogeneous populations structured by domain, topic difficulty, and linguistic style.

By Murilo Salem, Lu\'isa B\"ohm, Daniel Pontes, Anderson Ferrugem

llms efficiency benchmarks

arXiv AI

Aug 6

COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation

arXiv:2608. 04336v1 Announce Type: cross Abstract: Code generation systems make each LLM call with a model, a prompt, and decoding settings.

By Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova, Dong Huang, Mohammad Reza Mousavi, Mark Harman

llms

arXiv AI

Jun 11

APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection

arXiv:2606. 11459v1 Announce Type: cross Abstract: Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential.

By Fei Wang, Si Si, Cho-Jui Hsieh, Inderjit S. Dhillon

llms benchmarks

Related stories