The application of AI in psychiatric diagnosis faces significant challenges, including the subjective nature of mental health assessments, symptom overlap across disorders, and privacy constraints limiting data availability. To address these issues, we present MoodAngels, the first specialized multi-agent framework for mood disorder diagnosis. Our approach combines granular-scale analysis of clinical assessments with a structured verification process, enabling more accurate interpretation of complex psychiatric data. Complementing this framework, we introduce MoodSyn, an open-source dataset of 1,173 synthetic psychiatric cases that preserves clinical validity while ensuring patient privacy. Experimental results demonstrate that MoodAngels outperforms conventional methods, with our baseline agent achieving 12.3% higher accuracy than GPT-4o on real-world cases, and our full multi-agent system delivering further improvements. Evaluation in the MoodSyn dataset demonstrates exceptional fidelity, accurately reproducing both the core statistical patterns and complex relationships present in the original data while maintaining strong utility for machine learning applications. Together, these contributions provide both an advanced diagnostic tool and a critical research resource for computational psychiatry, bridging important gaps in AI-assisted mental health assessment.

Autonomous cyber-physical systems like robots and self-driving cars could greatly benefit from using formal methods to reason reliably about their control decisions. However, before a problem can be solved it needs to be stated. This requires writing a formal physics model of the cyber-physical system, which is a complex task that traditionally requires human expertise and becomes a bottleneck. This paper experimentally studies whether Large Language Models (LLMs) can automate the formalization process. A 20 problem benchmark suite is designed drawing from undergraduate level physics kinematics problems. In each problem, the LLM is provided with a natural language description of the objects' motion and must produce a model in differential game logic (dGL). The model is (1) syntax checked and iteratively refined based on parser feedback, and (2) semantically evaluated by checking whether symbolically executing the dGL formula recovers the solution to the original physics problem. A success rate of 70% (best over 5 samples) is achieved. We analyze failing cases, identifying directions for future improvement. This provides a first quantitative baseline for LLM-based autoformalization from natural language to a hybrid games logic with continuous dynamics.

Protecting privacy in social graphs requires preventing sensitive information, such as community affiliations, from being inferred by graph analysis, without substantially altering the graph topology. We address this through the problem of \emph{community membership hiding} (CMH), which seeks edge modifications that cause a target node to exit its original community, regardless of the detection algorithm employed. Prior work has focused on non-overlapping community detection, where trivial strategies often suffice, but real-world graphs are better modeled by overlapping communities, where such strategies fail. To the best of our knowledge, we are the first to formalize and address CMH in this setting. In this work, we propose a deep reinforcement learning (DRL) approach that learns effective modification policies, including the use of proxy nodes, while preserving graph structure. Experiments on real-world datasets show that our method significantly outperforms existing baselines in both effectiveness and efficiency, offering a principled tool for privacy-preserving graph modification with overlapping communities.

Thinking agents for zero-shot generalization to qualitatively novel tasks The Obelisk Team Astera Institute Emeryville, USA Abstract Intelligent organisms can solve truly novel problems which they have never encountered before, either in their lifetime or their evolution. An important component of this capacity is the ability to "think", that is, to mentally manipulate objects, concepts and behaviors in order to plan and evaluate possible solutions to novel problems, even without environment interaction. To generate problems that are truly qualitatively novel, while still solvable zero-shot (by mental simulation), we use the combinatorial nature of environments: we train the agent while withholding a specific combination of the environment's elements. The novel test task, based on this combination, is thus guaranteed to be truly novel, while still mentally simulable since the agent has been exposed to each individual element (and their pairwise interactions) during training. We propose a method to train agents endowed with world models to make use their mental simulation abilities, by selecting tasks based on the difference between the agent's pre-thinking and post-thinking performance. When tested on the novel, withheld problem, the resulting agent successfully simulated alternative scenarios and used the resulting information to guide its behavior in the actual environment, solving the novel task in a single real-environment trial (zero-shot). 1 Introduction An important aspect of intelligence is the ability to handle novel problems. While simpler organisms are restricted to problems similar to these they have been exposed to during training, and fare badly when faced Correspondance: Thomas Miconi, thomas.miconi@gmail.comwith An major component of this capacity is the ability to think before acting. By'thinking' 1, that is, by internally manipulating concepts and behaviors and evaluating likely outcomes, agents can tackle novel problems never encountered before, by recombining existing knowledge into new solutions. This ability is perhaps the hallmark of what we think of as truly "intelligent" behavior: it is highly prevalent in humans, but is is debated whether it even exists in non-human animals [Suddendorf and Busby, 2003], including mammals such as rodents [Gillespie et al., 2021] or even great apes [Suddendorf et al., 2009, Os-vath, 2010]. Much work in machine learning has focused on training agents with increasingly complex innate behaviors.

Digging up treasures from the past is an exciting business. So exciting, in fact, it's kept players coming back to the Tomb Raider series for nearly three decades. The original trilogy was successfully remastered and rereleased last year. Now a new collection has been recovered from the attic and put on show, like a family heirloom on the Antiques Roadshow. But will this turn out to be the gaming equivalent of a priceless Ming vase?

Generative models have become widely used in biomedical entity linking (BioEL) due to their excellent performance and efficient memory usage. However, these models are usually trained only with positive samples--entities that match the input mention's identifier--and do not explicitly learn from hard negative samples, which are entities that look similar but have different meanings. To address this limitation, we introduce ANGEL (Learning from Negative Samples in Generative Biomedical Entity Linking), the first framework that trains generative BioEL models using negative samples. Specifically, a generative model is initially trained to generate positive samples from the knowledge base for given input entities. Subsequently, both correct and incorrect outputs are gathered from the model's top-k predictions. The model is then updated to prioritize the correct predictions through direct preference optimization. Our models fine-tuned with ANGEL outperform the previous best baseline models by up to an average top-1 accuracy of 1.4% on five benchmarks. When incorporating our framework into pre-training, the performance improvement further increases to 1.7%, demonstrating its effectiveness in both the pre-training and fine-tuning stages. Our code is available at https://github.com/dmis-lab/ANGEL.

When Christi Angel first talked to a chatbot impersonating her deceased partner, Cameroun, she found the encounter surreal and "very weird". "Yes, I knew it was an AI system but, once I started chatting, my feeling was I was talking to Cameroun. That's how real it felt to me," she says. Angel's conversation with "Cameroun" took a more sinister turn when the persona assumed by the chatbot said he was "in hell". Angel, a practising Christian, found the exchange upsetting and returned a second time seeking a form of closure, which the chatbot provided.

While a drone superhighway might sound better suited to a science-fiction blockbuster than the Midlands, it's set to become a reality this summer. The world's first drone superhighway will open in the UK between June and early July, allowing pilotless drones to make high-speed deliveries across the country. Developed by drone software provider Altitude Angel, the 165-mile-long Skyway network will connect Coventry in the Midlands to Milton Keynes in the Southeast. However, sceptics have warned that the drone highway'inevitably poses risk' for the privacy and safety of Britons living in its flight path. Speaking to MailOnline, Chris Cole, director of campaign group Drone Wars, said: 'While the drone industry are incredibly happy about this, for people who end up living under the drones it may well end up being super annoying and super intrusive.'

A woman has a text chat with her long-dead lover. A family gets to hear a deceased elder speak again. A mother gets another chance to say goodbye to her child, who died suddenly, via a digital facsimile. This isn't a preview of the next season of Black Mirror -- these are all true stories from the Sundance documentary Eternal You, a fascinating and frightening dive into tech companies using AI to digitally resurrect the dead. It's yet another way modern AI, which includes large language models like ChatGPT and similar bespoke solutions, has the potential to transform society.

What do our creations think of us? Generative Pre-trained Transformer 3 is a language model released by OpenAI in 2020 that uses deep learning to produce text that seems like it could have been written by a human. Taken individually, the AI's lines don't smack much of poetry or strictly cohere, but in aggregate, they gesture at something more. What would it produce if asked to meditate on the human soul and to produce spiritual poetry like ours? What does it think of our religious beliefs?