Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans, with recent works extending this idea to visual domains using Vision-Language Models (VLMs). However, a rigorous comparison with methods that plan directly with VLMs is missing, due to a lack of visual benchmarks that support symbolic planning. We present ViPlan, the first open-source benchmark for comparing VLM-grounded symbolic approaches (VLM-as-grounder) with direct VLM planning methods (VLM-as-planner). ViPlan introduces a series of increasingly challenging tasks in two visual domains: a visual variant of the classic Blocksworld planning problem and a simulated household robotics environment. We find VLM-as-grounder methods to outperform direct VLM planning in Blocksworld (solving 46% of the tasks against 9%), where image grounding is both crucial and accurate. However, in the household robotics tasks, where linguistic knowledge helps, VLM-as-planner methods are greatly superior to VLM-as-grounder approaches (solving 34% of the tasks against 5%), which are hindered by partial observability. Thus, ViPlan domains capture fundamental shortcomings of both planning approaches, which we further diagnose with a qualitative failure analysis. Finally, across methods, we observe no consistent benefit from Chain-of-Thought prompting, suggesting persistent limitations in current VLMs’ visual reasoning abilities.

Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can repeat systematic errors. We study how to learn a cheap autonomous policy from an online, expensive, and imperfect VLM teacher. We propose SAGE (Selective Agent Guidance via Entropy), a framework that queries a VLM only when the learner is uncertain, executes the suggested action during training, and distills guidance into a lightweight Reinforcement Learning (RL) policy. Because VLM advice is not always reliable, SAGE can weight teacher-action distillation using environment-derived advantages rather than treating all suggestions as equally useful. Across sparse-reward visual reasoning and navigation tasks, SAGE learns policies that act without VLM guidance at evaluation time and improves over unguided RL in several environments, including settings where the learned policy exceeds its VLM teacher. The results show that selective guidance is most beneficial when the VLM can help the agent discover high-reward trajectories, and less useful when unguided exploration already succeeds or teacher actions do not lead to informative experience. SAGE also reduces VLM usage by prompting the teacher only on a fraction of training steps and requiring no VLM calls at deployment. Overall, our results suggest that VLMs don’t need to be used as fixed policies to be useful; they can instead act as temporary, imperfect sources of guidance whose value is tested and internalized through interaction.

Classification tasks require annotated data, which can often be expensive, time-consuming, or even unfeasible to collect.This is the case of the medical domain, where large datasets often have few annotated examples. To address this, we propose DecSelfMask (Decoder Self-learning by Masking), an approach to enhance decoder-only performance on classification tasks. We build on common self-learning approaches by leveraging a model to create training examples from unlabeled data, and propose a novel relevance-guided masking strategy.We use relevance attribution methods to determine what portions of unannotated texts are relevant for a task. We then create self-supervised training examples by masking out those portions, training the model to reconstruct them via next-token-prediction. We hypothesize that those examples convey knowledge about the structure and semantics of unannotated data that can be useful for downstream performance. We test our approach on 136 tasks from a collection of 1.9M clinical notes from an Italian hospital. We quantify DecSelfMask’s impact on downstream tasks on 5 models of different scales and families, including a probing analysis. Experiments show consistent gains, outperforming the base models (+9.1 points in Macro F1), continual pretraining (+6.3), synthetic label generation (+12.5), as well as common baselines. The results show that relevance attribution can serve as a powerful source of supervision for decoder learning from unlabeled data, beyond existing methods.

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating dialogues and handling a broad range of user queries. However, their effectiveness as end-to-end Task-Oriented Dialogue (TOD) systems remains limited due to their reliance on static parametric memory, which fails to accommodate evolving knowledge bases (KBs). This paper investigates a scalable function-calling approach that enables LLMs to retrieve only the necessary KB entries via schema-guided queries, rather than embedding the entire KB into each prompt. This selective retrieval strategy reduces prompt size and inference time while improving factual accuracy in system responses. We evaluate our method on the MultiWOZ 2.3 dataset and compare it against a full-KB baseline that injects the entire KB into every prompt. Experimental results show that our approach consistently outperforms the full-KB method in accuracy, while requiring significantly fewer input tokens and considerably less computation time, especially when the KB size increases.

We introduce MAIA (Multimodal AI Assessment), a native-Italian benchmark designed for fine-grained investigation of the reasoning abilities of visual language models on videos. MAIA differs from other available video benchmarks for its design, its reasoning categories, the metric it uses, and the language and culture of the videos. MAIA evaluates Vision Language Models (VLMs) on two aligned tasks: a visual statement verification task, and an open-ended visual question-answering task, both on the same set of video-related questions. It considers twelve reasoning categories that aim to disentangle language and vision relations by highlighting the role of the visual input. Thanks to its carefully taught design, it evaluates VLMs’ consistency and visually grounded natural language comprehension and generation simultaneously through an aggregated metric revealing low results that highlight models’ fragility. Last but not least, the video collection has been carefully selected to reflect the Italian culture, and the language data are produced by native-speakers.Data available at GitHub.

Despite the impressive capabilities of recent Large Language Models (LLMs) to generate human-like text, their ability to produce contextually appropriate content for specific communicative situations is still a matter of debate. This issue is particularly crucial when LLMs are employed as assistants to help solve tasks or achieve goals within a given conversational domain. In such scenarios, the assistant is expected to access specific knowledge (e.g., a database of restaurants, a calendar of appointments) that is not directly accessible to the user and must be consistently utilised to accomplish the task.In this paper, we conduct experiments to evaluate the trustworthiness of automatic assistants in task-oriented dialogues. Our findings indicate that state-of-the-art open-source LLMs still face significant challenges in maintaining logical consistency with a knowledge base of facts, highlighting the need for further advancements in this area.