cs.LGNov 19, 2026

Goal-Guided Reinforcement Learning via Fine-Tuning Vision-Language Models

Authors: Yajie Qi, Wei Wei, Lin Li, Lijun Zhang, Jianye Hao

Organizations: Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University · College of Intelligence and Computing, Tianjin University

Abstract

Exploration remains a major challenge for reinforcement learning (RL) agents in Craftax-style environments due to sparse rewards and long horizons. Large language models (LLMs) can guide exploration by generating high-level goals, but methods using models without explicit task adaptation often rely on carefully designed prompts and may produce inconsistent or contextually inappropriate goals. We introduce CCGP-2M, a multimodal goal-preference dataset constructed from interaction trajectories in Craftax-Classic, and propose a vision-language model (VLM)-guided RL framework that learns environment-specific goal guidance from this dataset. The framework consists of two stages: offline VLM fine-tuning and online goal-guided RL. In the offline stage, we align the VLM with goal preferences using Kullback-Leibler Token-level Direct Preference Optimization (KLTDPO), which combines token-level KL regularization with distributionally robust reweighting. Experiments on Craftax-Classic show that our method collects diamonds earlier than state-of-the-art baselines, achieves the highest score and reward, and attains the highest success rates on most achievements.

Figures & tables

Explore similar work

Sep 7, 2026

GIFT: Goal-Injected Fine-Tuning for Efficient Manipulation Policy Adaptation

Compared with relying solely on initial observations and language instructions, predicting goal images with generative models as high-level visual guidance can significantly enhance the robustness of Vision-Language-Action (VLA) models. However, most existing foundation models have not systematically incorporated goal image conditioning due to the high computational training cost. To this end, we propose Goal-Injected Fine-Tuning (GIFT), a lightweight and efficient fine-tuning framework that seamlessly integrates generated goal images into multiple representative pretrained VLA models. Our approach introduces goal image features into observations via a zero-initialized convolution which progressively grows parameters from zero and prevents harmful noise from disrupting the pretrained policy during fine-tuning. As training proceeds, goal information is gradually incorporated, enabling efficient goal understanding without disrupting model stability. We further introduce a refined image editing method to generate semantically and visually consistent goal images from initial observations and task instructions. Experiments show that goal-aware VLA models achieve substantial performance gains across tasks: with only a single epoch of fine-tuning, GIFT outperforms the base model by 6.0% and 13.4% on two SIMPLER settings, and by 4.7% on LIBERO, demonstrating both efficiency and effectiveness.
Nov 5, 2026

RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines

Reward machines (RMs) have been proposed as a reward formulation in reinforcement learning (RL) to capture non-Markovian tasks where credit assignment depends on history. By representing reward functions as automata, RMs expose the task's temporal structure and allow such rewards to be handled within a Markovian framework. However, they assume a labelling function, a proposition-grounding oracle for observations, which must be manually engineered for each environment, limiting their wider applicability. In this work, we address this limitation by proposing RM-VLM, a novel approach in which a large language model (LLM) generates an RM from a natural-language task description, and a vision-language model (VLM) acts as the labelling function, grounding the RM's propositions over image-based observations during RM-guided policy learning. A VLM-based value function estimator is used to assess the agent's progress towards each RM transition and derive a dense reward signal. We evaluate RM-VLM on three domains covering non-Markovian grid-world navigation, robotic manipulation, and 3D object collection. Our experimental results show that RM-VLM consistently achieves higher task success rates than existing VLM-based reward methods across all tested domains.
Sep 14, 2026

Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

Training prompts in online reinforcement learning (RL) differ substantially in how informative they are for the current policy: some are already saturated while others are too difficult to yield reliable learning signals, yet both receive equal rollout budget under standard training. We propose an exploration-guided prompt scaffolding framework that adapts the training prompt distribution dynamically throughout RL post-training of multimodal large language models (MLLMs). Central to our approach is the Exploration Potential Score(EPS)\textit{Exploration Potential Score} (EPS), a lightweight rollout-based proxy for prompt utility derived from KL-regularized policy improvement theory, computable directly from on-policy rollout statistics without additional overhead. Rather than discarding low-utility prompts, we use a teacher model to generate scaffolded rewrites that preserve the original task intent while making subsequent training more informative, reframing teacher supervision as training-data refinement rather than output imitation. Integrated with GRPO on Geo3K and MMK12, our method consistently outperforms the baseline on both in-domain and out-of-distribution benchmarks, achieving up to 9.7% relative improvement in-domain and gains of 11.5% on MathVision and 11.1% on MMMU-Pro.