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%.
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
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
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
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
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
The paper introduces BudgetAPO, a single‑stage prompt optimizer designed for tight‑budget scenarios where only a few hundred model calls are feasible. BudgetAPO adapts the evaluation slice size to each task’s noise level, uses a fixed slice to turn accept/reject decisions into paired comparisons, and applies a reflective operator to jointly rewrite reasoning strategy and output format. Across seven benchmarks and five subject models, BudgetAPO outperforms existing methods, ranking first on every subject and requiring far fewer calls to achieve comparable or superior performance.
By Haoyue Liu, Zhichao Wang, Huanyu Yan, Xiaoying Tang
arXiv:2609.21208v1 Announce Type: new
Abstract: Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but...
By Ana Nunez, Peyman Najafirad
The paper investigates how iterative language‑model optimizers improve prompts and programs by evaluating candidates, exposing failing cases to a proposer model, and retaining revisions that enhance performance. By conducting 1,750 pre‑registered experiments across nine benchmarks, the authors disentangle the effects of parent inheritance (keeping a surviving parent) from feedback disclosure (providing failure summaries) under equal computational budgets. They find that greedy parent inheritance alone drives most optimization gains, outperforming seed‑reset strategies even when the latter receive comprehensive failure summaries or larger proposer models, and that the cost of proposer reflection is minimal compared to validation and minibatch gating.
By Shanglin Yang, Zhan Shi
arXiv:2605.28360v3 Announce Type: replace
Abstract: Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, most existing methods treat each task's p...
By Jyotirmoy Nath, Neeraj Kumar, Brejesh Lall
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
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