arXiv:2603.18046v1 Announce Type: cross Abstract: When users query proprietary LLM APIs, they receive outputs with no cryptographic assurance that the claimed model was actually used. Service providers could substitute cheaper models, apply aggressive quantization, or return cached responses – all undetectable by users paying premium prices for frontier capabilities. We present METHOD, a zero-knowledge proof […]
CoDA: Exploring Chain-of-Distribution Attacks and Post-Hoc Token-Space Repair for Medical Vision-Language Models
arXiv:2603.18545v1 Announce Type: cross Abstract: Medical vision–language models (MVLMs) are increasingly used as perceptual backbones in radiology pipelines and as the visual front end of multimodal assistants, yet their reliability under real clinical workflows remains underexplored. Prior robustness evaluations often assume clean, curated inputs or study isolated corruptions, overlooking routine acquisition, reconstruction, display, and delivery […]
Lightweight Adaptation for LLM-based Technical Service Agent: Latent Logic Augmentation and Robust Noise Reduction
arXiv:2603.18074v1 Announce Type: cross Abstract: Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity arising from the diversity of valid responses. These limitations severely hinder agents from internalizing latent decision dynamics and generalizing effectively. Moreover, practical adaptation is often […]
Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control
arXiv:2603.19136v1 Announce Type: cross Abstract: Stock markets exhibit regime-dependent behavior where prediction models optimized for stable conditions often fail during volatile periods. Existing approaches typically treat all market states uniformly or require manual regime labeling, which is expensive and quickly becomes stale as market dynamics evolve. This paper introduces an adaptive prediction framework that adaptively […]
Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner
arXiv:2603.18088v1 Announce Type: cross Abstract: Constraints are essential for stabilizing reinforcement learning fine-tuning (RFT) and preventing degenerate outputs, yet they inherently conflict with the optimization objective because stronger constraints limit the ability of a fine-tuned model to discover better solutions. We propose textitdynamic constraints that resolve this tension by adapting to the evolving capabilities of […]
Agentic LLM Framework for Adaptive Decision Discourse
arXiv:2502.10978v2 Announce Type: replace Abstract: Effective decision-making in complex systems requires synthesizing diverse perspectives to address multifaceted challenges under uncertainty. This study introduces an agentic Large Language Models (LLMs) framework for simulating decision discourse – the deliberative process through which actionable strategies are collaboratively developed. Unlike traditional decision-support tools, this framework simulates diverse stakeholder personas, […]
Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
arXiv:2603.18101v1 Announce Type: cross Abstract: Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we […]
ClawTrap: A MITM-Based Red-Teaming Framework for Real-World OpenClaw Security Evaluation
arXiv:2603.18762v1 Announce Type: cross Abstract: Autonomous web agents such as textbfOpenClaw are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static sandbox settings and content-level prompt attacks, which leaves a practical gap for network-layer security testing. In this paper, we present […]
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
arXiv:2603.18113v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objective in trustworthy AI. This challenge becomes even more pronounced when aligning multiple, potentially conflicting human values. Although recent approaches, such as reward reweighting, prompt-based supervised […]
Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections
arXiv:2603.18914v1 Announce Type: cross Abstract: The rapid proliferation of artificial intelligence (AI) technologies has led to a dynamic regulatory landscape, where legislative frameworks strive to keep pace with technical advancements. As AI paradigms shift towards greater autonomy, specifically in the form of agentic AI, it becomes increasingly challenging to precisely articulate regulatory stipulations. This challenge […]
Understanding Task Aggregation for Generalizable Ultrasound Foundation Models
arXiv:2603.18123v1 Announce Type: cross Abstract: Foundation models promise to unify multiple clinical tasks within a single framework, but recent ultrasound studies report that unified models can underperform task-specific baselines. We hypothesize that this degradation arises not from model capacity limitations, but from task aggregation strategies that ignore interactions between task heterogeneity and available training data […]
Steering Awareness: Detecting Activation Steering from Within
arXiv:2511.21399v3 Announce Type: replace-cross Abstract: Activation steering — adding a vector to a model’s residual stream to modify its behavior — is widely used in safety evaluations as if the model cannot detect the intervention. We test this assumption, introducing steering awareness: a model’s ability to infer, during its own forward pass, that a steering […]