arXiv:2603.12277v1 Announce Type: cross Abstract: Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models infer roles from how text is written, not where it comes from. We design novel role probes to capture how models internally identify “who is speaking.” These reveal why prompt […]
Evaluating VLMs’ Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences
arXiv:2603.13100v1 Announce Type: cross Abstract: Understanding user instructions and object spatial relations in surrounding environments is crucial for intelligent robot systems to assist humans in various tasks. The natural language and spatial reasoning capabilities of Vision-Language Models (VLMs) have the potential to enhance the generalization of robot planners on new tasks, objects, and motion specifications. […]
Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning
arXiv:2603.12290v1 Announce Type: cross Abstract: Scholarly web is a vast network of knowledge connected by citations. However, this system is increasingly compromised by miscitation, where references do not support or even contradict the claims they are cited for. Current miscitation detection methods, which primarily rely on semantic similarity or network anomalies, struggle to capture the […]
Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel
arXiv:2603.12483v1 Announce Type: new Abstract: Across many domains (e.g., IoT, observability, telecommunications, cybersecurity), there is an emerging adoption of conversational data analysis agents that enable users to “talk to your data” to extract insights. Such data analysis agents operate on timeseries data models; e.g., measurements from sensors or events monitoring user clicks and actions in […]
Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
arXiv:2603.12298v1 Announce Type: cross Abstract: Activation engineering enables precise control over Large Language Models (LLMs) without the computational cost of fine-tuning. However, existing methods deriving vectors from static activation differences are susceptible to high-dimensional noise and layer-wise semantic drift, often capturing spurious correlations rather than the target intent. To address this, we propose Global Evolutionary […]
Multi-Agent Guided Policy Optimization
arXiv:2507.18059v2 Announce Type: replace Abstract: Due to practical constraints such as partial observability and limited communication, Centralized Training with Decentralized Execution (CTDE) has become the dominant paradigm in cooperative Multi-Agent Reinforcement Learning (MARL). However, existing CTDE methods often underutilize centralized training or lack theoretical guarantees. We propose Multi-Agent Guided Policy Optimization (MAGPO), a novel framework […]
HCP-DCNet: A Hierarchical Causal Primitive Dynamic Composition Network for Self-Improving Causal Understanding
arXiv:2603.12305v1 Announce Type: cross Abstract: The ability to understand and reason about cause and effect — encompassing interventions, counterfactuals, and underlying mechanisms — is a cornerstone of robust artificial intelligence. While deep learning excels at pattern recognition, it fundamentally lacks a model of causality, making systems brittle under distribution shifts and unable to answer “what-if” […]
Towards unified brain-to-text decoding across speech production and perception
arXiv:2603.12628v1 Announce Type: new Abstract: Speech production and perception are the main ways humans communicate daily. Prior brain-to-text decoding studies have largely focused on a single modality and alphabetic languages. Here, we present a unified brain-to-sentence decoding framework for both speech production and perception in Mandarin Chinese. The framework exhibits strong generalization ability, enabling sentence-level […]
Thermodynamics of Reinforcement Learning Curricula
arXiv:2603.12324v1 Announce Type: cross Abstract: Connections between statistical mechanics and machine learning have repeatedly proven fruitful, providing insight into optimization, generalization, and representation learning. In this work, we follow this tradition by leveraging results from non-equilibrium thermodynamics to formalize curriculum learning in reinforcement learning (RL). In particular, we propose a geometric framework for RL by […]
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
arXiv:2602.23163v2 Announce Type: replace Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quantify such behaviours are lacking. Classical definitions of steganography, and detection methods based on them, require a known reference distribution of non-steganographic signals. For the […]
Dual-Laws Model for a theory of artificial consciousness
arXiv:2603.12662v1 Announce Type: new Abstract: Objectively verifying the generative mechanism of consciousness is extremely difficult because of its subjective nature. As long as theories of consciousness focus solely on its generative mechanism, developing a theory remains challenging. We believe that broadening the theoretical scope and enhancing theoretical unification are necessary to establish a theory of […]
Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection
arXiv:2603.12349v1 Announce Type: cross Abstract: Scientific discovery increasingly relies on AI systems to select candidates for expensive experimental validation, yet no principled, budget-aware evaluation framework exists for comparing selection strategies — a gap intensified by large language models (LLMs), which generate plausible scientific proposals without reliable downstream evaluation. We introduce the Budget-Sensitive Discovery Score (BSDS), […]