arXiv:2603.20101v1 Announce Type: new Abstract: Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverage large language models (LLMs) at increasing levels of autonomy, ranging from fixed one-shot workflows to fully autonomous interpretability agents. This shift creates a […]
TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems
arXiv:2603.19452v1 Announce Type: cross Abstract: We introduce TrustFlow, a reputation propagation algorithm that assigns each software agent a multi-dimensional reputation vector rather than a scalar score. Reputation is propagated through an interaction graph via topic-gated transfer operators that modulate each edge by its content embedding, with convergence to a unique fixed point guaranteed by the […]
A Framework for Formalizing LLM Agent Security
arXiv:2603.19469v1 Announce Type: cross Abstract: Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However, existing definitions of security attacks […]
Learning Dynamic Belief Graphs for Theory-of-mind Reasoning
arXiv:2603.20170v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning with Large Language Models (LLMs) requires inferring how people’s implicit, evolving beliefs shape what they seek and how they act under uncertainty — especially in high-stakes settings such as disaster response, emergency medicine, and human-in-the-loop autonomy. Prior approaches either prompt LLMs directly or use latent-state […]
TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility
arXiv:2603.19474v1 Announce Type: cross Abstract: High-quality GPS trajectories are essential for location-based web services and smart city applications, including navigation, ride-sharing and delivery. However, due to low sampling rates and limited infrastructure coverage during data collection, real-world trajectories are often sparse and feature unevenly distributed location points. Recovering these trajectories into dense and continuous forms […]
Linear Social Choice with Few Queries: A Moment-Based Approach
arXiv:2603.19510v1 Announce Type: cross Abstract: Most social choice rules assume access to full rankings, while current alignment practice — despite aiming for diversity — typically treats voters as anonymous and comparisons as independent, effectively extracting only about one bit per voter. Motivated by this gap, we study social choice under an extreme communication budget in […]
Depictions of Depression in Generative AI Video Models: A Preliminary Study of OpenAI’s Sora 2
arXiv:2603.19527v1 Announce Type: cross Abstract: Generative video models are increasingly capable of producing complex depictions of mental health experiences, yet little is known about how these systems represent conditions like depression. This study characterizes how OpenAI’s Sora 2 generative video model depicts depression and examines whether depictions differ between the consumer App and developer API […]
FDARxBench: Benchmarking Regulatory and Clinical Reasoning on FDA Generic Drug Assessment
arXiv:2603.19539v1 Announce Type: cross Abstract: We introduce an expert curated, real-world benchmark for evaluating document-grounded question-answering (QA) motivated by generic drug assessment, using the U.S. Food and Drug Administration (FDA) drug label documents. Drug labels contain rich but heterogeneous clinical and regulatory information, making accurate question answering difficult for current language models. In collaboration with […]
CageDroneRF: A Large-Scale RF Benchmark and Toolkit for Drone Perception
arXiv:2601.03302v2 Announce Type: replace-cross Abstract: We present CageDroneRF (CDRF), a large-scale benchmark for Radio-Frequency (RF) drone detection and identification built from real-world captures and systematically generated synthetic variants. CDRF addresses the scarcity and limited diversity of existing RF datasets by coupling extensive raw recordings with a principled augmentation pipeline that (i)~precisely controls Signal-to-Noise Ratio (SNR), […]
LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News Detection
arXiv:2603.19293v1 Announce Type: cross Abstract: Multimodal fake news detection is crucial for mitigating societal disinformation. Existing approaches attempt to address this by fusing multimodal features or leveraging Large Language Models (LLMs) for advanced reasoning. However, these methods suffer from serious limitations, including a lack of comprehensive multi-view judgment and fusion, and prohibitive reasoning inefficiency due […]
CDEoH: Category-Driven Automatic Algorithm Design With Large Language Models
arXiv:2603.19284v1 Announce Type: cross Abstract: With the rapid advancement of large language models (LLMs), LLM-based heuristic search methods have demonstrated strong capabilities in automated algorithm generation. However, their evolutionary processes often suffer from instability and premature convergence. Existing approaches mainly address this issue through prompt engineering or by jointly evolving thought and code, while largely […]
TempPerturb-Eval: On the Joint Effects of Internal Temperature and External Perturbations in RAG Robustness
arXiv:2512.01183v2 Announce Type: replace-cross Abstract: The evaluation of Retrieval-Augmented Generation (RAG) systems typically examines retrieval quality and generation parameters like temperature in isolation, overlooking their interaction. This work presents a systematic investigation of how text perturbations (simulating noisy retrieval) interact with temperature settings across multiple LLM runs. We propose a comprehensive RAG Perturbation-Temperature Analysis Framework […]