Natural Language Actor-Critic: Scalable Off-Policy Learning in Language Space

LongVT has been introduced as an innovative framework designed to enhance video reasoning capabilities in large multimodal models (LMMs) by facilitating a process known as 'Thinking with Long Videos.' This approach utilizes a global-to-local reasoning loop, allowing models to focus on specific video clips and retrieve relevant visual evidence, thereby addressing challenges associated with long-form video processing.

A novel framework named LangSAT has been introduced, which integrates reinforcement learning (RL) with natural language processing (NLP) to enhance Boolean satisfiability (SAT) solving. This system allows users to input standard English descriptions, which are then converted into Conjunctive Normal Form (CNF) expressions for solving, thus improving accessibility and efficiency in SAT-solving processes.

UW-BioNLP presented their methods for extracting chemotherapy timelines from clinical notes at the ChemoTimelines 2025 shared task, focusing on strategies like chain-of-thought thinking and supervised fine-tuning. Their best-performing model, fine-tuned Qwen3-14B, achieved a score of 0.678 on the test set leaderboard.

A recent study published on arXiv investigates the use of generic masculines (GM) in contemporary German press texts, analyzing their distribution and linguistic characteristics. The research focuses on lexeme-specific differences among personal nouns, revealing significant variations, particularly between passive role nouns and prestige-related personal nouns, based on a corpus of 6,195 annotated tokens.

Recent research has uncovered a limit cycle organization in the articulatory movements that generate human speech, challenging the conventional view of speech as discrete actions. This study reveals that rhythmicity, often associated with acoustic energy and neuronal excitations, is also present in the motor activities involved in speech production.

Recent research highlights the limitations of hierarchical instruction schemes in large language models (LLMs), revealing that these models struggle with consistent instruction prioritization, even in simple cases. The study introduces a systematic evaluation framework to assess how effectively LLMs enforce these hierarchies, finding that the common separation of system and user prompts fails to create a reliable structure.

CARL, a new reinforcement learning algorithm, has been introduced to optimize multi-step agents by focusing on critical actions that significantly influence outcomes, rather than treating all actions equally. This approach aims to enhance the efficiency and performance of training and inference processes in complex task environments.

A new approach to medication recommendation utilizing multi-large language model (LLM) collaboration has been proposed, addressing the critical challenge of reliability in AI-driven clinical decision support. This method builds on previous work in LLM Chemistry, focusing on enhancing the stability and credibility of recommendations derived from brief clinical vignettes.