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...
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.
The paper "Demystifying Reinforcement Learning Post-Training of Language Models" investigates how reinforcement learning (RL) post‑training enhances large language models (LLMs) for tasks such as reasoning, math, and coding. By isolating RL components in a controlled setting, the authors analyze how the base model’s prior distribution, reward granularity, prompt diversity, and model scale influence outcomes, using policy entropy to compare pre‑training, supervised fine‑tuning (SFT), and RL stages. The study clarifies the role of spurious rewards, the importance of the base model’s probability mass on desired behaviors, and how these factors interact to determine post‑training success, offering a practical primer for NLP researchers. "whyItMatters":"The work provides a clearer understanding of RL post‑training mechanics, helping researchers and practitioners effectively apply RL to improve LLM capabilities."
arXiv:2607. 21419v1 Announce Type: new Abstract: In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimization.
arXiv:2608.24696v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training lar...
arXiv:2608.23830v1 Announce Type: cross Abstract: RL has emerged as a powerful paradigm for enhancing the instruction following capabilities of LLMs. While existing training recipes achieve substanti...
arXiv:2606. 27814v4 Announce Type: replace Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.
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:2607. 04412v1 Announce Type: new Abstract: Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals.
arXiv:2606. 27814v1 Announce Type: new Abstract: Training small language-model agents for long-horizon interactive tasks requires both fast imitation and reward-driven improvement.
arXiv:2604. 00860v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a central post-training paradigm for improving the reasoning capabilities of large language models.
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.