The return to the wasteland is way better than just okie dokie. The follow-up to a successful debut is often harder to make than the first, and that goes double when the inspiration for a show comes from the most beloved installment of the underlying franchise . That's precisely the challenge season 2 is facing as the TV series shifts its stage to the irradiated lights of New Vegas when the series returns on December 16 at 9PM ET/6PM PT on Prime Video . However, while other video game adaptations like suffered from a bit of a sophomore slump, continues to get more crass, vulgar and abrasive in the most entertaining ways. Season two picks up directly after the first as Lucy (played by Ella Purnelle) and The Ghoul (Walton Goggins) make their way across the wasteland in pursuit of Lucy's father.

How did extinct animals move? Paleontologists are interested in figuring this out since it can tell us more about their ways of life, such as whether they were agile enough to hunt prey. It can also provide clues about how locomotion evolved; for example, when our ancestors started to walk upright. Researchers have come up with hypotheses about the movement of long-gone species by examining evidence such as fossilized bones or well-preserved footprints. Extinct animals can also be compared to similar living ones: comparing their limb length, for example, can give an idea of their speed of movement.

We propose a structure to represent the social fabric of a group. We call it the `cohesion network' of the group. It can be seen as a graph whose vertices are strict subgroups and whose edges indicate a prescribed `pro-social behaviour' from one subgroup towards another. In social psychology, pro-social behaviours are building blocks of full-blown cooperation, which we assimilate here with `group cohesiveness'. We then define a formal framework to study cohesive group agency. To do so, we simply instantiate pro-social behaviour with the more specific relation of `successful assistance' between acting entities in a group. The relations of assistance within a group at the moment of agency constitute the social fabric of the cohesive group agency. We build our logical theory upon the logic of agency "bringing-it-about". We obtain a family of logics of cohesive group agency, one for every class of cohesion networks.

Small language models (SLMs) are inherently limited in knowledge-intensive tasks due to their constrained capacity. While test-time computation offers a path to enhanced performance, most approaches treat reasoning as a fixed or heuristic process. In this work, we propose a new paradigm: viewing the model's internal reasoning, delimited by and tags, as a dynamic task vector machine. Rather than treating the content inside these tags as a mere trace of thought, we interpret the generation process itself as a mechanism through which the model \textbf{constructs and refines its own task vectors} on the fly. We developed a method to optimize this dynamic task vector machine through RLVR and successfully trained an agentic web-search model. We present Lucy, a 1.7B-parameter SLM that leverages this dynamic reasoning mechanism with MCP integration to achieve 78.3% accuracy on the SimpleQA benchmark, performing on par with much larger models such as DeepSeek-V3. This demonstrates that small models can rival large ones when equipped with structured, self-constructed task reasoning.

We investigate Controlled Query Evaluation (CQE) over ontologies, where information disclosure is regulated by epistemic dependencies (EDs), a family of logical rules recently proposed for the CQE framework. In particular, we combine EDs with the notion of optimal GA censors, i.e. maximal sets of ground atoms that are entailed by the ontology and can be safely revealed. We focus on answering Boolean unions of conjunctive queries (BUCQs) with respect to the intersection of all optimal GA censors - an approach that has been shown in other contexts to ensure strong security guarantees with favorable computational behavior. First, we characterize the security of this intersection-based approach and identify a class of EDs (namely, full EDs) for which it remains safe. Then, for a subclass of EDs and for DL-Lite_R ontologies, we show that answering BUCQs in the above CQE semantics is in AC^0 in data complexity by presenting a suitable, detailed first-order rewriting algorithm. Finally, we report on experiments conducted in two different evaluation scenarios, showing the practical feasibility of our rewriting function.

The film Her features Samantha, a sophisticated AI audio agent who is capable of understanding both linguistic and paralinguistic information in human speech and delivering real-time responses that are natural, informative and sensitive to emotional subtleties. Moving one step toward more sophisticated audio agent from recent advancement in end-to-end (E2E) speech systems, we propose LUCY, a E2E speech model that (1) senses and responds to user's emotion, (2) deliver responses in a succinct and natural style, and (3) use external tool to answer real-time inquiries. Experiment results show that LUCY is better at emotion control than peer models, generating emotional responses based on linguistic emotional instructions and responding to paralinguistic emotional cues. Lucy is also able to generate responses in a more natural style, as judged by external language models, without sacrificing much performance on general question answering. Finally, LUCY can leverage function calls to answer questions that are out of its knowledge scope.

Language models (LMs) have been widely used to generate text on the Internet. The generated text is often collected into the training corpus of the next generations of LMs. Previous work has experimentally found that LMs collapse when trained on recursively generated text. This paper contributes to existing knowledge from two aspects. We present a theoretical proof of LM collapse. Our proof reveals the cause of LM collapse and proves that all auto-regressive LMs will definitely collapse. We present a new finding: the performance of LMs gradually declines when trained on recursively generated text until they perform no better than a randomly initialized LM. The trained LMs produce large amounts of repetitive text and perform poorly across a wide range of natural language tasks. The above proof and new findings deepen our understanding of LM collapse and offer valuable insights that may inspire new training techniques to mitigate this threat.

Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to problems that are more complex than the ones on which they have been trained. Empirical investigations of such questions are impeded by two major flaws of current evaluations: (i) much of the evaluation data is contaminated, in the sense that it has already been seen during training, and (ii) benchmark datasets do not capture how problem proofs may be arbitrarily complex in various ways. As a step towards addressing these issues, we present a framework for evaluating LLMs on problems with arbitrarily complex arithmetic proofs, called MathGAP. MathGAP generates problems that follow fixed proof specifications -- along with chain-of-thought reasoning annotations -- enabling systematic studies on generalization with respect to arithmetic proof complexity. We apply MathGAP to analyze how in-context learning interacts with generalization to problems that have more complex proofs. We find that among the models tested, most show a significant decrease in performance as proofs get deeper and wider. This effect is more pronounced in complex, nonlinear proof structures, which are challenging even for GPT-4o. Surprisingly, providing in-context examples from the same distribution as the test set is not always beneficial for performance. In particular, zero-shot prompting as well as demonstrating a diverse range of examples that are less complex than the test data sometimes yield similar or higher accuracies.

Large Language Models (LLMs) have made significant progress in assisting users to query databases in natural language. While LLM-based techniques provide state-of-the-art results on many standard benchmarks, their performance significantly drops when applied to large enterprise databases. The reason is that these databases have a large number of tables with complex relationships that are challenging for LLMs to reason about. We analyze challenges that LLMs face in these settings and propose a new solution that combines the power of LLMs in understanding questions with automated reasoning techniques to handle complex database constraints. Based on these ideas, we have developed a new framework that outperforms state-ofthe-art techniques in zero-shot text-to-SQL on complex benchmarks.

Planet Earth is about to receive a special delivery -- the biggest sample yet from an asteroid. A United States space agency (NASA) spacecraft will fly by Earth on Sunday and drop off what is expected to be at least a cupful of rubble it grabbed from the asteroid Bennu, closing out a seven-year quest. The sample capsule will parachute into the Utah desert as its mothership, the OSIRIS-REx spacecraft, zooms off for an encounter with another asteroid. Scientists anticipate getting about 250g (0.5lb) of pebbles and dust, much more than the teaspoon or so brought back by Japan from two other asteroids. No other country has fetched pieces of asteroids, preserved time capsules from the dawn of our solar system that can help explain how Earth -- and life -- came to be.