Reinforcement learning (RL) has demonstrated considerable potential for enhancing reasoning in large language models (LLMs). However, existing methods suffer from Gradient Starvation and Policy Degradation when training directly on samples with mixed difficulty. To mitigate this, prior approaches leverage Chain-of-Thought (CoT) data, but the construction of high-quality CoT annotations remains labor-intensive. Alternatively, curriculum learning strategies have been explored but frequently encounter challenges, such as difficulty mismatch, reliance on manual curriculum design, and catastrophic forgetting. To address these issues, we propose AdaCuRL, a Adaptive Curriculum Reinforcement Learning framework that integrates coarse-to-fine difficulty estimation with adaptive curriculum scheduling. This approach dynamically aligns data difficulty with model capability and incorporates a data revisitation mechanism to mitigate catastrophic forgetting. Furthermore, AdaCuRL employs adaptive reference and sparse KL strategies to prevent Policy Degradation. Extensive experiments across diverse reasoning benchmarks demonstrate that AdaCuRL consistently achieves significant performance improvements on both LLMs and MLLMs.

Abstract--Audio Descriptions (AD) are essential for making visual content accessible to individuals with visual impairments. Recent works have shown a promising step towards automating AD, but they have been limited to describing high-quality movie content using human-annotated ground truth AD in the process. In this work, we present an end-to-end pipeline, MCAD, that extends AD generation beyond movies to the domain of sports, with a focus on soccer games, without relying on ground truth AD. T o address the absence of domain-specific AD datasets, we fine-tune a Video Large Language Model on publicly available movie AD datasets so that it learns the narrative structure and conventions of AD. During inference, MCAD incorporates multimodal contextual cues such as player identities, soccer events/actions, and commentary from the game. These cues, combined with input prompts to the fine-tuned Video-LLM, allow the system to produce complete AD text for each video segment. We further introduce a new evaluation metric, ARGE-AD, designed to accurately assess the quality of generated AD. ARGE-AD evaluates the generated AD for the presence of five characteristics: (i) usage of people's names, (ii) mention of actions/events, (iii) appropriate length of AD, (iv) absence of pronouns, and (v) overlap from commentary/subtitles. We present an in-depth analysis of our approach on both movie and soccer datasets. We also validate the use of this metric to quantitatively comment on the quality of generated AD using our metric across domains. Additionally, we contribute audio descriptions for 100 soccer game clips annotated by two AD experts. Audio Description (AD) is the descriptive spoken narration of visual content, primarily for assisting visual impairments in accessing visual content [1].

We propose a method that uses large language models to assist graph machine learning under personalization and privacy constraints. The approach combines data augmentation for sparse graphs, prompt and instruction tuning to adapt foundation models to graph tasks, and in-context learning to supply few-shot graph reasoning signals. These signals parameterize a Dynamic UMAP manifold of client-specific graph embeddings inside a Bayesian variational objective for personalized federated learning. The method supports node classification and link prediction in low-resource settings and aligns language model latent representations with graph structure via a cross-modal regularizer. We outline a convergence argument for the variational aggregation procedure, describe a differential privacy threat model based on a moments accountant, and present applications to knowledge graph completion, recommendation-style link prediction, and citation and product graphs. We also discuss evaluation considerations for benchmarking LLM-assisted graph machine learning.

Predicting an individual's personalities from their generated texts is a challenging task, especially when the text volume is large. In this paper, we introduce a straightforward yet effective novel strategy called targeted preselection of texts (TPoT). This method semantically filters the texts as input to a deep learning model, specifically designed to predict a Big Five personality trait, facet, or item, referred to as the BIG5-TPoT model. By selecting texts that are semantically relevant to a particular trait, facet, or item, this strategy not only addresses the issue of input text limits in large language models but also improves the Mean Absolute Error and accuracy metrics in predictions for the Stream of Consciousness Essays dataset.

Research in Machine Learning (ML) and AI evolves rapidly. Information Extraction (IE) from scientific publications enables to identify information about research concepts and resources on a large scale and therefore is a pathway to improve understanding and reproducibility of ML-related research. To extract and connect fine-grained information in ML-related research, e.g. method training and data usage, we introduce GSAP-ERE. It is a manually curated fine-grained dataset with 10 entity types and 18 semantically categorized relation types, containing mentions of 63K entities and 35K relations from the full text of 100 ML publications. We show that our dataset enables fine-tuned models to automatically extract information relevant for downstream tasks ranging from knowledge graph (KG) construction, to monitoring the computational reproducibility of AI research at scale. Additionally, we use our dataset as a test suite to explore prompting strategies for IE using Large Language Models (LLM). We observe that the performance of state-of-the-art LLM prompting methods is largely outperformed by our best fine-tuned baseline model (NER: 80.6%, RE: 54.0% for the fine-tuned model vs. NER: 44.4%, RE: 10.1% for the LLM). This disparity of performance between supervised models and unsupervised usage of LLMs suggests datasets like GSAP-ERE are needed to advance research in the domain of scholarly information extraction.

The mismatch between the growing demand for psychological counseling and the limited availability of services has motivated research into the application of Large Language Models (LLMs) in this domain. Consequently, there is a need for a robust and unified benchmark to assess the counseling competence of various LLMs. Existing works, however, are limited by unprofessional client simulation, static question-and-answer evaluation formats, and unidimensional metrics. These limitations hinder their effectiveness in assessing a model's comprehensive ability to handle diverse and complex clients. To address this gap, we introduce \textbf{CARE-Bench}, a dynamic and interactive automated benchmark. It is built upon diverse client profiles derived from real-world counseling cases and simulated according to expert guidelines. CARE-Bench provides a multidimensional performance evaluation grounded in established psychological scales. Using CARE-Bench, we evaluate several general-purpose LLMs and specialized counseling models, revealing their current limitations. In collaboration with psychologists, we conduct a detailed analysis of the reasons for LLMs' failures when interacting with clients of different types, which provides directions for developing more comprehensive, universal, and effective counseling models.

Current Multimodal Large Language Models exhibit very strong performance for several demanding tasks. While commercial MLLMs deliver acceptable performance in low-resource languages, comparable results remain unattained within the open science community. In this paper, we aim to develop a strong MLLM for a low-resource language, namely Basque. For that purpose, we develop our own training and evaluation image-text datasets. Using two different Large Language Models as backbones, the Llama-3.1-Instruct model and a Basque-adapted variant called Latxa, we explore several data mixtures for training. We show that: i) low ratios of Basque multimodal data (around 20%) are already enough to obtain solid results on Basque benchmarks, and ii) contrary to expected, a Basque instructed backbone LLM is not required to obtain a strong MLLM in Basque. Our results pave the way to develop MLLMs for other low-resource languages by openly releasing our resources.

Large language models have recently demonstrated remarkable abilities to self-correct their responses through iterative refinement, often referred to as self-consistency or self-reflection. However, the dynamics of this self-correction mechanism may differ substantially depending on whether the model is tasked with open-ended text generation or with selecting the most appropriate response from multiple predefined options. In this paper, we conduct a systematic investigation of these two paradigms by comparing performance trends and error-correction behaviors across various natural language understanding and reasoning tasks, covering language models of different scales and families. Our experimental results reveal distinct patterns of improvement and failure modes: \textit{While open-ended generation often benefits from the flexibility of re-interpretation and compositional refinement, multiple-choice selection can leverage clearer solution boundaries but may be limited by the provided options}. This contrast also reflects the dual demands faced by emerging agentic LLM applications: effective agents must not only generate and refine open-ended plans or explanations, but also make reliable discrete choices when operating within constrained action spaces. Our findings, therefore, highlight that the design of self-correction mechanisms should take into account the interaction between task structure and output space, with implications for both knowledge-intensive reasoning and decision-oriented applications of LLMs.

The capacity of Large Language Models (LLMs) for reasoning remains an active area of research, with the capabilities of frontier models continually advancing. We provide an updated evaluation of the end-to-end planning performance of three frontier LLMs as of 2025, where models are prompted to generate a plan from PDDL domain and task descriptions. We evaluate DeepSeek R1, Gemini 2.5 Pro, GPT-5 and as reference the planner LAMA on a subset of domains from the most recent Learning Track of the International Planning Competition. Our results show that on standard PDDL domains, the performance of GPT-5 in terms of solved tasks is competitive with LAMA. When the PDDL domains and tasks are obfuscated to test for pure reasoning, the performance of all LLMs degrades, though less severely than previously reported for other models. These results show substantial improvements over prior generations of LLMs, reducing the performance gap to planners on a challenging benchmark.

The use of large language models (LLMs) for evaluating outputs is becoming an increasingly effective and scalable approach. However, it remains uncertain whether this capability extends beyond task-specific evaluations to more general assessments of text quality, particularly in multilingual contexts. In this study, we introduce, MTQ-Eval, a novel framework for multilingual text quality evaluation that learns from examples of both high- and low-quality texts, adjusting its internal representations. To develop MTQ-Eval, we first automatically generate text quality preference data and then use it to train open-source base LLMs to align with ratings of high- and low-quality text. Our comprehensive evaluation across 115 languages demonstrates the improved performance of the proposed model. Upon further analysis, we find that this enhanced evaluation capability also leads to notable improvements in downstream tasks.