arXiv Computation and Language October 21, 2026 By Xiaofan Zhou, Lu Cheng

Explore More, Validate Less: Efficient Reflective Prompt Optimization

Read the original on arXiv Computation and Language →

The paper introduces a two‑stage framework for reflective prompt optimization that separates candidate generation from validation. In the construction stage, multiple parents are sampled and their training responses reused across parallel reflection branches, with each revision screened on a small minibatch to allow locally improved candidates to propagate without full validation. In the exploration stage, a fixed full‑validation budget is used to select the best prompt from a frozen candidate pool, enabling independent control of pool size and validation effort. Experiments on five benchmarks with Qwen3.5‑9B and Llama‑3.1‑8B‑Instruct show that retaining 100 candidates and performing 20 full validations can improve performance by up to 11.22 percentage points over the initial solver, and learned selection consistently outperforms the initial solver across all comparisons.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning

Jun 4

CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts

arXiv:2606. 04661v1 Announce Type: cross Abstract: Prompts tuned for accuracy often grow long, raising inference cost on every model call.

By Shanu Kumar, Shubhanshu Khandelwal, Akhila Yesantarao Venkata, Parag Agrawal, Yova Kementchedjhieva, Manish Gupta

llms benchmarks

arXiv Computation and Language

Oct 1

AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt Optimization

arXiv:2609.39927v1 Announce Type: new Abstract: Prompt optimization improves the performance of language-model systems on downstream tasks by refining their prompts. Classical methods evaluate prompt...

By Junyang Chen, Zecheng Wang, Jingbang Chen

benchmarks

arXiv AI

Aug 21

Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection

arXiv:2608. 20169v1 Announce Type: cross Abstract: We present a novel approach to efficient LLM agent harness optimization through adaptive validation task selection.

By Atsuyuki Miyai, Kiyoharu Aizawa, Toshihiko Yamasaki

llms agents nlp

arXiv Computation and Language

Sep 17

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

arXiv:2607.28077v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identica...

By Shuang Liang, Haoyang Zhou, Yifan Gong, Guowei Wang, Xiting Wang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Oct 23

GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer

GFlowPO introduces a probabilistic framework for optimizing language model prompts by treating prompt search as posterior inference over latent prompts, regularized by a meta-prompted reference-LM prior. The method first fine‑tunes a lightweight prompt‑LM using an off‑policy Generative Flow Network objective that reuses past prompt evaluations for sample‑efficient exploration. It then applies a training‑free Dynamic Memory Update to refine the meta‑prompt with diverse and top‑performing prompts, leading to consistent improvements over recent discrete prompt optimization baselines on few‑shot classification, instruction induction, and question‑answering tasks.

By Junmo Cho, Suhan Kim, Sangjune An, Minsu Kim, Dong Bok Lee, Heejun Lee, Sung Ju Hwang, Hae Beom Lee

llms nlp reinforcement-learning fine-tuning benchmarks

arXiv AI

Aug 26

Exploit More, Explore Smarter for Budget-Constrained Agentic Search

The paper introduces ExTS, a tree‑search policy designed for budget‑constrained agentic search where evaluation and generation costs are high. ExTS treats expansion as a value‑of‑information decision, combining discriminative reward shaping, a stochastic virtual child, and quality‑conditioned branching to allocate budget more effectively. Experiments on prompt optimization, code generation, molecular structure elucidation, and agentic workflow optimization show ExTS matching or surpassing task‑specific baselines with an average gain of +5.5% using a single configuration, and the authors also present pilot‑run diagnostics to guide adaptation to different problem structures.

By Haoyang Fang, Bernie Wang

llms agents