arXiv:2605.22963v1 Announce Type: cross Abstract: Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs […]
Population-Specific Genetic and Non-Genetic Influences on Sleep Traits and Health Outcomes
arXiv:2605.23521v1 Announce Type: new Abstract: Sleep traits are shaped by genetic and environmental factors and may influence many health conditions. The All of Us Research Program, which includes EHR, physical measurements, genomic data, and wearable data across ancestry groups, provides an opportunity to study genetic and non-genetic contributors to sleep-related health outcomes. We examined associations […]
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
arXiv:2605.23590v1 Announce Type: new Abstract: ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow, redundant, or poorly targeted trajectories. Prior work has explored rubrics as external quality signals, but […]
One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
arXiv:2605.23652v1 Announce Type: new Abstract: On a 300-persona life-simulation benchmark, pcsp achieves compositional zero-shot persona identification up to 17x above chance, Spearman rho approx 0.73 semantic-behavioral alignment, and 22x faster inference than an LLM-as-policy baseline. Life simulation games require hundreds to thousands of non-player characters (NPCs) that behave consistently with distinct personalities while remaining controllable […]
On the Design of an Analog-Dyadic Converter CRN
arXiv:2605.23745v1 Announce Type: new Abstract: The Chemical Reaction Networks (CRN) interpreted through the differential semantics, even when restricted to elementary reactions with mass action law kinetics, form a Turing-complete language. This means that any computable real function can thus be programmed, and in fact compiled, in an abstract CRN that will compute it with an […]
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
arXiv:2605.23780v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieves strong reliability and locality, it often exhibits limited generality, failing to propagate edits across semantically equivalent visual and linguistic variations. This issue arises from the lack of explicit semantic […]
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
arXiv:2605.23899v1 Announce Type: new Abstract: Language agents increasingly improve by reusing emphskills — structured procedural artifacts distilled from past experience. In particular, emphdomain-level and emphmodel-generated skills are especially promising. They offer fast adaptation within a domain by encoding domain-specific recurring procedures, and they scale beyond labor-intensive hand-crafting. However, while extraction methods continue to proliferate, understanding […]
An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Using Edge Intelligence
arXiv:2605.22824v1 Announce Type: cross Abstract: Environmental monitoring is a crucial component of the smart city infrastructure. It enables informed decision making which enhances sustainability, public health and urban planning. However, the large-scale deployments of the smart sensors have raised concerns on excessive energy consumption and redundant data collection as well as limited sensor lifespan. To […]
Evaluating Large Language Models in a Complex Hidden Role Game
arXiv:2605.22826v1 Announce Type: cross Abstract: Quantifying the deceptive potential of Large Language Models (LLMs) is critical for AI safety, yet difficult to achieve in uncontrolled environments. This work investigates the reasoning, persuasion, and deceptive capabilities of LLMs within the social deduction game Secret Hitler. I introduce an open-source framework and novel metrics to measure performance: […]
LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding
arXiv:2605.22829v1 Announce Type: cross Abstract: Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coarse-grained page-level retrieval, which fails to capture fine-grained semantic and layout structures in visually rich documents, thereby compromising retrieval accuracy and leading to […]
The Cognitive Kardashev Scale: Quantifying the Material Envelope of Civilisational Computation
arXiv:2605.22840v1 Announce Type: cross Abstract: How much thinking can a civilisation do? Kardashev’s (1964) typology ranks civilisations by total power: planetary (Type I, ~10^16 W), stellar (Type II, ~10^26 W), galactic (Type III). This paper builds an analogous Cognitive Kardashev Scale: how much sustained AI-grade computation each tier could support. Four ingredients enter the calculation: […]
The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems
arXiv:2605.22842v1 Announce Type: cross Abstract: Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the emphMisattribution Gap, where memory-layer attacks produce behaviors indistinguishable from model failure, causing defenders to apply the wrong remediation. We formalize emphSemantic Norm Drift (SND) as a third path to […]