arXiv:2604.22102v1 Announce Type: cross Abstract: Many robotic tasks are unforgiving; a single mistake in a dynamic throw can lead to unacceptable delays or unrecoverable failure. To mitigate this, we present a novel approach that leverages learned simulation priors to inform goal-conditioned dynamic manipulation of ropes for efficient and accurate task execution. Related methods for dynamic […]
Reliable Self-Harm Risk Screening via Adaptive Multi-Agent LLM Systems
arXiv:2604.22154v1 Announce Type: cross Abstract: Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not indicate when a decision is reliable or how errors may accumulate across multiple LLM judgements, limiting their suitability […]
ReCast: Recasting Learning Signals for Reinforcement Learning in Generative Recommendation
arXiv:2604.22169v1 Announce Type: cross Abstract: Generic group-based RL assumes that sampled rollout groups are already usable learning signals. We show that this assumption breaks down in sparse-hit generative recommendation, where many sampled groups never become learnable at all. We propose ReCast, a repair-then-contrast learning-signal framework that first restores minimal learnability for all-zero groups and then […]
Evaluating LLM-Based Goal Extraction in Requirements Engineering: Prompting Strategies and Their Limitations
arXiv:2604.22207v1 Announce Type: cross Abstract: Due to the textual and repetitive nature of many Requirements Engineering (RE) artefacts, Large Language Models (LLMs) have proven useful to automate their generation and processing. In this paper, we discuss a possible approach for automating the Goal-Oriented Requirements Engineering (GORE) process by extracting functional goals from software documentation through […]
Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning
arXiv:2604.22229v1 Announce Type: cross Abstract: One-step offline RL actors are attractive because they avoid backpropagating through long iterative samplers and keep inference cheap, but they still have to improve under a critic without drifting away from actions that the dataset can support. In recent one-step extraction pipelines, a strong iterative teacher provides one target action […]
A Probabilistic Framework for Hierarchical Goal Recognition
arXiv:2604.22256v1 Announce Type: cross Abstract: Goal recognition aims to infer an agent’s goal from observations of its behaviour. In realistic settings, recognition can benefit from exploiting hierarchical task structure and reasoning under uncertainty. Planning-based goal recognition has made substantial progress over the past decade, but to the best of our knowledge no existing approach jointly […]
ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification
arXiv:2604.22292v1 Announce Type: cross Abstract: The classification of legal documents from an unstructured data corpus has several crucial applications in downstream tasks. Documents relevant to court filings are key in use cases such as drafting motions, memos, and outlines, as well as in tasks like docket summarisation, retrieval systems, and training data curation. Current methods […]
Spontaneous Persuasion: An Audit of Model Persuasiveness in Everyday Conversations
arXiv:2604.22109v1 Announce Type: cross Abstract: Large language models (LLMs) possess strong persuasive capabilities that outperform humans in head-to-head comparisons. Users report consulting LLMs to inform major life decisions in relationships, medical settings, and when seeking professional advice. Prior work measures persuasion as intentional attempts at producing the most effective argument or convincing statement. This fails […]
When AI Speaks, Whose Values Does It Express? A Cross-Cultural Audit of Individualism-Collectivism Bias in Large Language Models
arXiv:2604.22153v1 Announce Type: cross Abstract: When you ask an AI assistant for advice about your career, your marriage, or a conflict with your family, does it give you the same answer regardless of where you are from? We tested this systematically by presenting three leading AI systems (Claude Sonnet 4.5, GPT-5.4, and Gemini 2.5 Flash) […]
MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization
arXiv:2604.21937v1 Announce Type: new Abstract: Computational drug discovery, particularly the complex workflows of drug molecule screening and optimization, requires orchestrating dozens of specialized tools in multi-step workflows, yet current AI agents struggle to maintain robust performance and consistently underperform in these high-complexity scenarios. Here we present MolClaw, an autonomous agent that leads drug molecule evaluation, […]
Error-free Training for MedMNIST Datasets
arXiv:2604.18916v2 Announce Type: replace Abstract: In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be trained error-free, thus acquiring the capability of not making repeated mistakes. The method is applied to 18 MedMNIST biomedical datasets. Except for three datasets, which suffer from […]
A theory for coexistence and selection of branched actin networks in a shared and finite pool of monomers
arXiv:2511.23344v2 Announce Type: replace Abstract: Cellular actin structures are continuously turned over while keeping similar sizes. Since they all compete for a shared pool of actin monomers, the question arises how they can coexist in these dynamic steady states. Recently, the coexistence of branched actin networks with different densities growing in a shared and finite […]