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.
arXiv:2607. 28657v1 Announce Type: new Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users.
The paper introduces EXPO, an algorithm that automatically optimizes the meta-prompt—specifically the task description and meta-instruction—for large language model agents in sequential decision-making tasks such as Bayesian optimization and multi-armed bandits. Building on adversarial bandit techniques to handle non-stationary rewards, the authors extend EXPO to EXPO-ES, which also optimizes exemplars (historical interactions) within the meta-prompt. Experiments demonstrate that these methods significantly improve the performance of LLM-based agents in sequential decision-making scenarios.
arXiv:2610.19408v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) have advanced rapidly, yet strengthening their reasoning through reinforcement learning (RL) remains an open ch...
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...
arXiv:2607. 08837v1 Announce Type: cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers.
arXiv:2508. 10123v3 Announce Type: replace-cross Abstract: Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT).
arXiv:2310.04363v3 Announce Type: replace Abstract: Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits t...
arXiv:2606. 06828v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences.
The paper introduces Diffusion Meta-Prompt (DMP), a framework that learns a distribution of prompts via diffusion models, enabling the synthesis of new prompts from natural language task descriptions without needing original task data or losses. DMP incorporates a test-time steering strategy that uses a best training prompt as a latent anchor to stabilize sampling, improving generalization across classification, retrieval, and text-to-image generation tasks. The method reduces storage and inference costs by over 90% compared to prompt retrieval, achieves up to 2.0% average gains over prior meta-learning methods on composite classification, and provides a theoretical bound on expected task loss.
The paper introduces an exploration-guided prompt scaffolding framework for multimodal large language models, dynamically adjusting the prompt distribution during reinforcement learning post-training. It uses an Exploration Potential Score (EPS) derived from KL-regularized policy improvement to assess prompt utility without extra overhead, and a teacher model rewrites low-utility prompts to preserve intent while improving informativeness. Experiments on Geo3K, MMK12, MathVision, and MMMU-Pro show consistent performance gains, up to 9.7% in-domain and over 11% on out-of-distribution benchmarks.
arXiv:2607.08837v4 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject...
The paper introduces LM2LM, a method that trains large language models (LLMs) to propose improvements for other LLMs using reinforcement learning (RL). It employs a frozen research world model (RWM) to predict the gains of proposals, providing a cheaper surrogate reward, and periodically validates high‑scoring proposals to keep feedback reliable. Experiments across eight LM development environments show that LM2LM enables a Qwen3.8‑27B model to outperform GPT‑6‑sol on held‑out tasks while reducing data‑generation cost by 33%, and it generalizes to unseen model families.