arXiv:2605.13280v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are transforming software development, the functional quality of generated code has become a central focus, leaving readability, one of critical non-functional attributes, understudied. Given that LLM-generated code still needs human review before adoption, it is important to understand its readability especially compared with human-written code […]
PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models
arXiv:2605.12835v1 Announce Type: new Abstract: Large language models can extract local causal claims from text, but those claims become more useful when organized as persistent, navigable world models rather than as flat summaries. We introduce PROMETHEUS, a framework that turns retrieved literature, filings, reviews, reports, agent traces, source data, code, simulations, and scientific models into […]
Why the Unfinished Keeps Returning: Canxianization and the Dynamics of Conscious Priority
arXiv:2605.12543v1 Announce Type: new Abstract: Some conscious contents disappear after access; others return repeatedly, long after their triggering conditions have ceased. We propose Canxianization as the process by which a perturbation becomes closure-resistant self-relevant unfinishedness and thereby acquires recurrent conscious priority. The theory distinguishes this phenomenon from emotional arousal, memory strength, the Zeigarnik effect, curiosity, […]
Multimodal Hidden Markov Models for Persistent Emotional State Tracking
arXiv:2605.12838v1 Announce Type: new Abstract: Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understanding and guiding communication in applied, especially clinical, conversational contexts. Existing approaches to emotion recognition operate at the utterance level, obscuring the persistent phases that characterize real conversational […]
OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics Research
arXiv:2605.13618v1 Announce Type: cross Abstract: The Materials Genome Initiative catalyzed the proliferation of centralized platforms–SaaS, PaaS, and IaaS–that aggregate computational and experimental resources for accelerated materials discovery. In parallel, breakthroughs in large language models (LLMs) and autonomous agents have created powerful new reasoning capabilities for scientific research. Yet a critical “last mile” problem remains: while […]
Inline Critic Steers Image Editing
arXiv:2605.12724v1 Announce Type: cross Abstract: Instruction-based image editing exhibits heterogeneous difficulty not only across cases but also across regions of an image, motivating refinement approaches that allocate correction to where the model struggles. Existing refinement signals arrive late, after a fully generated image or a completed denoising step. We ask whether such a signal can […]
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
arXiv:2605.13734v1 Announce Type: cross Abstract: LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit payload crossing network and storage boundaries, making KV a dominant end-to-end bottleneck. Existing KV compression […]
Multi-Quantile Regression for Extreme Precipitation Downscaling
arXiv:2605.12762v1 Announce Type: cross Abstract: Deep super-resolution networks for precipitation downscaling achieve strong bulk skill yet systematically under-predict the heavy-tail events that drive flood risk. We demonstrate that the primary obstacle is the loss function, not the data: under intensity-weighted MAE, real and synthetic labels at the same input are simply averaged, meaning data augmentation […]
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
arXiv:2605.12894v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly deployed in settings where they interact with a wide variety of people, including users who are unclear, impatient, or reluctant to share information. However, collecting real interaction data at scale remains expensive. The field has turned to LLM-based user simulators as stand-ins, but […]
WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
arXiv:2605.13846v1 Announce Type: cross Abstract: This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman, an endangered Australian indigenous language into English. The significant challenge we face is the lack of large-scale training data: in fact, we only have 6 hours of annotated audio. Therefore, while it is common practice […]
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
arXiv:2605.12813v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, motivating the need for realistic adversarial prompts that elicit such failures. We formulate hallucination elicitation as a constrained optimization problem, where the goal is to find semantically coherent adversarial prompts that are equivalent to benign […]
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
arXiv:2605.12922v1 Announce Type: new Abstract: Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and rules. This degradation has been measured behaviorally but not mechanistically explained. We propose a channel-transition account: goal-defining tokens become less accessible through attention, while goal-related […]