arXiv:2605.20998v1 Announce Type: cross Abstract: Aspect-Term Sentiment Analysis (ATSA) in multi-aspect sentences faces a fundamental tradeoff between efficiency and expressiveness. Existing models either re-encode the sentence for each aspect or rely on static use of deep representations, leading to redundant computation and limited adaptivity. We argue that Transformer depth is a costly, queryable resource, and […]
Hybrid Machine Learning Model for Forest Height Estimation from TanDEM-X and Landsat Data
arXiv:2605.20997v1 Announce Type: cross Abstract: Integrating machine learning (ML) with physical models (PM) has emerged as a promising way of retrieving geophysical parameters from remote sensing data. In this context, a ML model for estimating forest height from TanDEM-X interferometric coherence measurements has recently been proposed, that constrains the learning process through a PM. While […]
MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
arXiv:2603.06007v2 Announce Type: replace-cross Abstract: Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. MAS workflows can be naturally modeled as directed computation graphs, where nodes execute agents or sub-workflows and edges encode dependencies and message passing. However, implementing complex graph workflows in current […]
Argus: Evidence Assembly for Scalable Deep Research Agents
arXiv:2605.16217v3 Announce Type: replace-cross Abstract: Deep research agents have achieved remarkable progress on complex information seeking tasks. Even long ReAct style rollouts explore only a single trajectory, while recent state of the art systems scale inference time compute via parallel search and aggregation. Yet deep research answers are composed of complementary pieces of evidence, which […]
PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment
arXiv:2605.21225v1 Announce Type: cross Abstract: We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs could be numerically encoded, we assume a more general setting is when costs are provided as preferences. Given a reward-optimized policy and a small dataset of […]
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
arXiv:2603.14184v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question answering (VQA) tasks. We identify attention dispersion as the underlying cause: during multi-step reasoning, the model’s visual attention becomes scattered and drifts away from question-relevant regions, effectively “losing focus” on the visual […]
Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence
arXiv:2603.26603v2 Announce Type: replace-cross Abstract: The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced privacy and offline accessibility, but this transition encounters a harsh reality: the physical constraints of mobile batteries, thermal limits, and, most importantly, memory constraints. To navigate this landscape, we constructed a replicable and reproducible experimental […]
Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems
arXiv:2605.14259v2 Announce Type: replace Abstract: Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding and auditable execution required for these complex environments. We introduce HEAR, an enterprise agentic reasoner built on a Stratified Hypergraph Ontology. Its […]
Cell State Transitions Beyond the Small-Noise Limit
arXiv:2510.07797v3 Announce Type: replace-cross Abstract: State transitions are fundamental in biological systems but challenging to observe directly. Here, we present the first single-cell observation of state transitions in a synthetic bacterial genetic circuit. Using a mother machine, we tracked over 1007 cells for 27 hours. First-passage analysis and dynamical reconstruction reveal that transitions occur outside […]
TelecomTS: A Multi-Modal Observability Dataset for Time Series and Language Analysis
arXiv:2510.06063v2 Announce Type: replace Abstract: Modern enterprises generate vast streams of time series metrics when monitoring complex systems, known as observability data. Unlike conventional time series from domains such as climate, observability data are zero-inflated, highly stochastic, and exhibit minimal temporal structure. Despite their importance, observability datasets remain underrepresented in public benchmarks due to proprietary […]
Quality and Security Signals in AI-Generated Python Refactoring Pull Requests
arXiv:2605.21453v1 Announce Type: cross Abstract: As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of their changes in real-world projects, particularly for refactoring-oriented contributions. It remains unclear how agent-authored refactoring edits affect maintainability, code quality, and security once merged into GitHub repositories. […]
Parallelized Hierarchical Connectome: A Spatiotemporal Recurrent Framework for Spiking State-Space Models
arXiv:2604.01295v2 Announce Type: replace Abstract: This work presents the Parallelized Hierarchical Connectome (PHC), a general architectural framework that upgrades temporal-only State-Space Models (SSMs) into spatiotemporal recurrent networks. Conventional SSMs achieve parallel-scan training but are limited to temporal recurrence, lacking lateral or feedback interactions within a single timestep. PHC maps the diagonal SSM core to a […]