arXiv:2605.15377v1 Announce Type: new Abstract: As AI systems are increasingly deployed in autonomous agentic settings at scale, it is important to ensure the actions they take are safe and aligned with user intent. Monitoring agent actions is a key safety mechanism, yet reliable monitors remain difficult to build and the scale of these systems makes […]
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
arXiv:2605.01970v3 Announce Type: replace-cross Abstract: Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work: the attacker plants a dormant payload […]
Sharp Spectral Thresholds for Logit Fixed Points
arXiv:2605.15651v1 Announce Type: cross Abstract: Softmax feedback systems are a common mathematical core of entropy-regularized reinforcement learning, logit game dynamics, population choice, and mean-field variational updates. Their central stability question is simple: when does a self-reinforcing softmax system produce a unique and globally predictable outcome? Classical theory gives a conservative answer. By treating softmax as […]
From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation
arXiv:2605.16026v1 Announce Type: cross Abstract: Compositional speech-to-speech translation (S2ST) systems built upon speech large language models (SpeechLLMs) have recently shown promising performance. However, existing S2ST systems often either neglect source-language information or encode it through a language-as-label paradigm, representing each source language as an independent flat embedding. Such a design overlooks systematic linguistic structure shared […]
Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration
arXiv:2509.21663v2 Announce Type: replace-cross Abstract: Neurosymbolic integration (NeSy) blends neural-network learning with symbolic reasoning. The field can be split between methods injecting hand-crafted rules into neural models, and methods inducing symbolic rules from data. We introduce Logic of Hypotheses (LoH), a novel language that unifies these strands, enabling the flexible integration of data-driven rule learning […]
VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
arXiv:2605.15672v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lack robust control over basic visual operations. We study textitline tracing, where a model must follow a selected visual path through successive local continuations. To isolate this ability, we design controlled tracing tasks that introduce nearby competitors while […]
Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs
arXiv:2605.12713v2 Announce Type: replace-cross Abstract: In the field of quantum reservoir computing (QRC), many different computational models and architectures have been proposed. From these models, we identify feedback-based models — which use a feedback mechanism to re-embed classical measurements from the QRC — and recurrent models — which use a multi-register approach with memory and […]
Beyond Partner Diversity: An Influence-Based Team Steering Framework for Zero-Shot Human-Machine Teaming
arXiv:2605.15400v1 Announce Type: new Abstract: While AI agents are rapidly advancing from isolated tools to interactive collaborators, data-driven human-machine teaming (HMT) methods remain costly in their reliance on human interaction data across domains, teammates, and team sizes. Zero-shot coordination (ZSC) addresses this bottleneck by simulating diverse partner populations to approximate how unseen partners might behave. […]
Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric Study
arXiv:2605.16011v1 Announce Type: cross Abstract: Adaptive learning refers to educational technologies that track learners’ learning progress and adapt the instructional process based on individual learners’ learning performance. It is increasingly recognized as critical for developing an effective learning support tool. Vision language models (VLMs) have seen adoption in mathematics education, and students have been using […]
$alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
arXiv:2605.15688v1 Announce Type: cross Abstract: Concept Activation Vectors (CAVs) are a fundamental tool for concept-based explainability in deep learning, yet their practical utility is limited by statistical instability. We analyze the stochastic nature of CAVs and the Testing with CAVs (TCAV) method, deriving the distributions of major CAV classes including PatternCAV, FastCAV, and ridge regression-based […]
Representing Higher-Order Networks: A Survey of Graph-Based Frameworks
arXiv:2605.12509v2 Announce Type: replace-cross Abstract: Many real-world phenomena are naturally modeled by graphs and networks. However, classical graph models are often limited to pairwise interactions and may not adequately capture the richer structures that arise in practice. Higher-order graph formalisms extend this framework by incorporating multiway, hierarchical, temporal, multilayer, recursive, and tensor-based interactions, thereby providing […]
CitePrism: Human-in-the-Loop AI for Citation Auditing and Editorial Integrity
arXiv:2605.16000v1 Announce Type: cross Abstract: Editors and reviewers are expected to ensure that manuscripts cite relevant, accurate, current, and ethically appropriate literature, yet manuscript-level citation auditing remains largely manual, fragmented, and difficult to scale. Citation context, metadata quality, self-citation patterns, and bibliographic integrity all affect whether a reference appropriately supports a local claim. We present […]