arXiv:2601.18747v1 Announce Type: cross Abstract: Modern information retrieval is transitioning from simple document filtering to complex, neuro-symbolic reasoning workflows. However, current retrieval architectures face a fundamental efficiency dilemma when handling the rigorous logical and arithmetic constraints required by this new paradigm. Standard iterator-based engines (Document-at-a-Time) do not natively support complex, nested logic graphs; forcing them […]
Introducing COGENT3: An AI Architecture for Emergent Cognition
arXiv:2504.04139v2 Announce Type: replace Abstract: This paper presents COGENT3 (or Collective Growth and Entropy-modulated Triads System), a novel approach for emergent cognition integrating pattern formation networks with group influence dynamics. Contrasting with traditional strategies that rely on predetermined architectures, computational structures emerge dynamically in our framework through agent interactions. This enables a more flexible and […]
The Art of Saying “Maybe”: A Conformal Lens for Uncertainty Benchmarking in VLMs
arXiv:2509.13379v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical dimension of uncertainty quantification has received insufficient attention. Therefore, unlike prior conformal prediction studies that focused on limited settings, we conduct a […]
SafeRBench: Dissecting the Reasoning Safety of Large Language Models
arXiv:2511.15169v3 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to justify harmful actions or conceal malicious intent behind lengthy intermediate steps. Most existing benchmarks only check the final output, missing how risks […]
MARO: Learning Stronger Reasoning from Social Interaction
arXiv:2601.12323v2 Announce Type: replace Abstract: Humans face countless scenarios that require reasoning and judgment in daily life. However, existing large language model training methods primarily allow models to learn from existing textual content or solve predetermined problems, lacking experience in real scenarios involving interaction, negotiation, and competition with others. To address this, this paper proposes […]
MEDIC: Comprehensive Evaluation of Leading Indicators for LLM Safety and Utility in Clinical Applications
arXiv:2409.07314v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) achieve superhuman performance on standardized medical licensing exams, these static benchmarks have become saturated and increasingly disconnected from the functional requirements of clinical workflows. To bridge the gap between theoretical capability and verified utility, we introduce MEDIC, a comprehensive evaluation framework establishing leading indicators across […]
Towards Interpretable Deep Generative Models via Causal Representation Learning
arXiv:2504.11609v2 Announce Type: replace-cross Abstract: Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art performance across wide-ranging domains. These methods’ surprising performance is due in part to their ability to learn implicit “representations” of complex, multi-modal data. Unfortunately, deep neural networks are […]
Enhancing Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation
arXiv:2506.01327v3 Announce Type: replace-cross Abstract: Federated Class-Incremental Learning (FCIL) enables Class-Incremental Learning (CIL) from distributed data. Existing FCIL methods typically integrate old knowledge preservation into local client training. However, these methods cannot avoid spatial-temporal client drift caused by data heterogeneity and often incur significant computational and communication overhead, limiting practical deployment. To address these challenges […]
Prompt to Pwn: Automated Exploit Generation for Smart Contracts
arXiv:2508.01371v2 Announce Type: replace-cross Abstract: Smart contracts are important for digital finance, yet they are hard to patch once deployed. Prior work mostly studies LLMs for vulnerability detection, leaving their automated exploit generation (AEG) capability unclear. This paper closes that gap with textscReX, a framework that links LLM-based exploit synthesis to the Foundry stack for […]
FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
arXiv:2509.14275v3 Announce Type: replace-cross Abstract: Privacy-preserving adaptation of Large Language Models (LLMs) in sensitive domains (e.g., mental health) requires balancing strict confidentiality with model utility and safety. We propose FedMentor, a federated fine-tuning framework that integrates Low-Rank Adaptation (LoRA) and domain-aware Differential Privacy (DP) to meet per-domain privacy budgets while maintaining performance. Each client (domain) […]
TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
arXiv:2510.08048v3 Announce Type: replace-cross Abstract: Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference […]
Distillation-Enabled Knowledge Alignment for Generative Semantic Communications of AIGC Images
arXiv:2506.19893v2 Announce Type: replace-cross Abstract: Due to the surging amount of AI-generated images, its provisioning to edges and mobile users from the cloud incurs substantial traffic on networks. Generative semantic communication (GSC) offers a promising solution by transmitting highly compact information, i.e., prompt text and latent representations, instead of high-dimensional image data. However, GSC relies […]