Playlist generation based on textual queries using large language models (LLMs) is becoming an important interaction paradigm for music streaming platforms. User queries span a wide spectrum from highly personalized intent to essentially catalog-style requests. Existing systems typically rely on non-personalized retrieval/ranking or apply a fixed level of preference conditioning to every query, which can overfit catalog queries to a single user or under-personalize explicitly listener-dependent requests. We present an industrial-scale LLM-based playlist generation system with dynamic personalization that adapts the personalization strength to the query type. We define a query taxonomy, train a query-type classifier on 5,000 manually labeled queries, and use its predicted probability to modulate the mixture of LLM-based semantic scoring and personalized evaluation. In a blind user study with pairwise comparisons and ELO aggregation, this approach consistently outperforms both non-personalized and fixed-personalization baselines.

Embodied Vision–Language–Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data. Yet we do not know whether these agents still "know the basics" about the world after adaptation, nor how much commonsense and factual knowledge is preserved versus catastrophically forgotten. When a VLA fails on a knowledge-sensitive task, it is unclear whether the failure reflects degraded world knowledge or merely poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge benchmarks to VLA evaluation by requiring agents to act to answer. We map each benchmark question to a discrete embodied answer-selection decision in a controlled tabletop environment, where the agent answers via a single object-placement action into the region corresponding to its selected option, producing an action-grounded success rate with reduced control confounds. We introduce layerwise intent probing–linear classifiers on per-layer representations predicting the agent’s option selection–to localize answer-relevant information across model depth. Evaluating 9 state-of-the-art VLA models, we rank them across basic commonsense and world-knowledge categories and find that answer-relevant signals peak in middle VLM-backbone layers but attenuate in upper backbone layers and the action head.

Recent progress in language models has been defined by scale, yet many practical applications benefit more from robust reasoning than extensive parametric knowledge. We introduce OCC-RAG, a family of models for faithful context-based QA, which prioritizes task-specific reasoning capabilities over knowledge capacity. To train OCC-RAG, we implement a novel pipeline synthesizing over three million multi-context, multi-hop QA examples that target multi-hop reasoning, strict context faithfulness, and calibrated abstention. Mid-trained on this corpus, the models produce structured reasoning traces with source citations grounded in literal quotes from the context. Despite their compact size, OCC-RAG models outperform their same-size general-purpose counterparts on every benchmark and exceed models 2–6× larger on financial reasoning (TAT-QA) and faithfulness (ConFiQA), attaining the best results among all evaluated open-weight models up to 32B parameters. On ConFiQA they rank behind only a frontier proprietary models; on multi-hop reasoning (HotpotQA, MuSiQue) and refusal (MuSiQue-Un) they are on par with 8B-class models and close much of the remaining gap to the largest evaluated systems. We release both our code and family of models.[<https://hf.co/collections/occ-ai/occ-rag>]

Vision Language Action (VLA) models are widely used in Embodied AI, enabling robots to interpret and execute language instructions. However, their robustness to natural language variability in real-world scenarios has not been thoroughly investigated.In this work, we present a novel systematic study of the robustness of state-of-the-art VLA models under linguistic perturbations. Specifically, we evaluate model performance under two types of instruction noise: (1) human-generated paraphrasing and (2) the addition of irrelevant context. We further categorize irrelevant contexts into two groups according to their length and their semantic and lexical proximity to robot commands. In this study, we observe consistent performance degradation as context size expands. We also demonstrate that the model can exhibit relative robustness to random context, with a performance drop within 10%, while semantically and lexically similar context of the same length can trigger a quality decline of around 50%. Human paraphrases of instructions lead to a drop of nearly 20%. Our results highlights a critical gap in the safety and efficiency of modern VLA models for real-world deployment.

Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation, where models generate segmentation masks based on textual queries. While prior work has primarily focused on perturbing image inputs, semantically equivalent textual paraphrases—crucial in real-world applications where users express the same intent in varied ways—remain underexplored. To address this gap, we introduce a novel adversarial paraphrasing task: generating grammatically correct paraphrases that preserve the original query meaning while degrading segmentation performance. To evaluate the quality of adversarial paraphrases, we develop a comprehensive automatic evaluation protocol validated with human studies. Furthermore, we introduce SPARTA—a black-box, sentence-level optimization method that operates in the low-dimensional semantic latent space of a text autoencoder, guided by reinforcement learning. SPARTA achieves significantly higher success rates, outperforming prior methods by up to 2x on both the ReasonSeg and LLMSeg-40k datasets. We use SPARTA and competitive baselines to assess the robustness of advanced reasoning segmentation models. We reveal that they remain vulnerable to adversarial paraphrasing—even under strict semantic and grammatical constraints. All code and data will be released publicly upon acceptance.