arXiv:2605.17413v1 Announce Type: cross Abstract: Safety-aligned language models often refuse cybersecurity requests whose wording resembles misuse, even when the task is authorized and defensive. This makes security evaluation ambiguous: a failed answer may reflect missing capability or refusal-policy intervention. Ablating Safety studies alignment removal as a controlled transformation-evaluation protocol for authorized security tasks, comparing authorized-context […]
EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
arXiv:2510.16079v3 Announce Type: replace-cross Abstract: Current Large Language Model (LLM) agents show strong performance in tool use, but lack the crucial capability to systematically learn from their own experiences. While existing frameworks mainly focus on mitigating external knowledge gaps, they fail to address a more fundamental limitation: the inability to iteratively refine problem-solving strategies. In […]
The End of Trust: How Agentic AI Breaks Security Assumptions
arXiv:2605.16436v1 Announce Type: cross Abstract: For decades, the security of digital interaction has rested on an unacknowledged economic constraint. Attackers faced a tradeoff between the fidelity of a deception and the scale at which it could be deployed. Convincing impersonation required sustained human effort and was confined to a narrow set of high-value targets, while […]
Automated Coding of Communication Data Using ChatGPT: Consistency Across Subgroups
arXiv:2510.20584v3 Announce Type: replace-cross Abstract: Assessing communication and collaboration at scale depends on a labor-intensive task of coding communication data into categories according to different frameworks. Prior research has established that ChatGPT can be directly instructed with coding rubrics to code the communication data and achieves accuracy comparable to human raters. However, whether the coding […]
MARS: Technical Report for the CASTLE Challenge at EgoVis 2026
arXiv:2605.18176v1 Announce Type: cross Abstract: This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participants must answer 185 closed-form questions over the CASTLE 2024 dataset. In contrast to prior single-video egocentric benchmarks, CASTLE requires reasoning over four days of activity, 15 synchronized perspectives, […]
Prior Knowledge Makes It Possible: From Sublinear Graph Algorithms to LLM Test-Time Methods
arXiv:2510.16609v3 Announce Type: replace-cross Abstract: Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model’s parametric knowledge and externally retrieved information. However, the theoretical underpinnings of this relationship remain poorly understood. Specifically, it is not clear how much pre-training knowledge is required to answer queries with a […]
Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery
arXiv:2605.17976v1 Announce Type: new Abstract: Scientific discovery is increasingly constrained by costly experiments and limited resources, underscoring the need for efficient optimization in AI for science. Bayesian Optimization (BO), though widely adopted for balancing exploration and exploitation, often exhibits slow cold-start performance and poor scalability in high-dimensional settings, limiting its applicability in real-world scientific problems. […]
Hierarchical Two-Stage Framework for Environment-Aware Long-Horizon Vessel Trajectory Prediction
arXiv:2605.16442v1 Announce Type: cross Abstract: Long-horizon vessel trajectory forecasting under real ocean conditions is critical for collision avoidance, traffic management, and route planning. However, achieving accurate predictions is challenging due to long-range temporal dependencies and dynamic environmental factors such as currents, wind, and waves. To address these issues, we propose a hierarchical two-stage framework that […]
FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation
arXiv:2509.19102v2 Announce Type: replace-cross Abstract: General-purpose robotic skills from end-to-end demonstrations often leads to task-specific policies that fail to generalize beyond the training distribution. Therefore, we introduce FunCanon, a framework that converts long-horizon manipulation tasks into sequences of action chunks, each defined by an actor, verb, and object. These chunks focus policy learning on the […]
FLAG: Foundation model representation with Latent diffusion Alignment via Graph for spatial gene expression prediction
arXiv:2605.18055v1 Announce Type: cross Abstract: Predicting spatial gene expression from routine H&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks, thereby overlooking essential biological structures like gene coordination and spatial distribution. To preserve these relationships, we introduce textbfFLAG, a diffusion-based framework that redefines this task as structured distribution modeling. At […]
UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
arXiv:2605.17285v1 Announce Type: cross Abstract: Node representation learning, such as Graph Neural Networks (GNNs), has emerged as a pivotal method in machine learning. The demand for reliable explanation generation surges, yet unsupervised models remain underexplored. To bridge this gap, we introduce a method for generating counterfactual (CF) explanations in unsupervised node representation learning. We identify […]
Byzantine-Resilient Federated Learning via QUBO-Based Client Selection on Quantum Annealers
arXiv:2605.16438v1 Announce Type: cross Abstract: Federated Learning (FL) trains a global model across decentralized clients while preserving data privacy, but at scale it is vulnerable to malicious updates. Byzantine-resilient aggregation methods such as MultiKrum score gradients against their nearest neighbors and can miss malicious updates that preserve the statistical properties of honest ones. We propose […]