arXiv:2603.07246v1 Announce Type: cross Abstract: Geospatial foundation models provide precomputed embeddings that serve as compact feature vectors for large-scale satellite remote sensing data. While these embeddings can reduce data-transfer bottlenecks and computational costs, Earth observation (EO) applications can still face geometric mismatches between user-defined areas of interest and the fixed precomputed embedding grid. Standard latent-space […]
Scheduling Parallel Optical Circuit Switches for AI Training
arXiv:2603.07373v1 Announce Type: cross Abstract: The rapid growth of AI training has dramatically increased datacenter traffic demand and energy consumption, which has motivated renewed interest in optical circuit switches (OCSes) as a high-bandwidth, energy-efficient alternative for AI fabrics. Deploying multiple parallel OCSes is a leading alternative. However, efficiently scheduling time-varying traffic matrices across parallel optical […]
Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems
arXiv:2603.07473v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based systems remains largely unexplored.In this work, we conduct a large-scale security analysis of MCP […]
Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural Context
arXiv:2603.07792v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly influence global digital ecosystems, yet their potential to perpetuate social and cultural biases remains poorly understood in underrepresented contexts. This study presents a systematic analysis of representational biases in seven state-of-the-art LLMs: GPT-4o-mini, Claude-3-Sonnet, Claude-4-Sonnet, Gemini-2.0-Flash, Gemini-2.0-Lite, Llama-3-70B, and Mistral-Nemo in the Nepali cultural context. […]
AI Agents, Language, Deep Learning and the Next Revolution in Science
arXiv:2603.07940v1 Announce Type: cross Abstract: Modern science is reaching a critical inflection point. Instruments across disciplines, from particle physics and astronomy to genomics and climate modeling, now produce data of such scale, diversity, and interdependence that traditional analytical methods can no longer keep pace. This growing imbalance between data generation and data understanding signals the […]
Dynamic Targeting of Satellite Observations Using Supplemental Geostationary Satellite Data and Hierarchical Planning
arXiv:2603.06719v1 Announce Type: cross Abstract: The Dynamic Targeting (DT) mission concept is an approach to satellite observation in which a lookahead sensor gathers information about the upcoming environment and uses this information to intelligently plan observations. Previous work has shown that DT has the potential to increase the science return across applications. However, DT mission […]
Agent Hunt: Bounty Based Collaborative Autoformalization With LLM Agents
arXiv:2603.06737v1 Announce Type: cross Abstract: We describe an experiment in large-scale autoformalization of algebraic topology in an Interactive Theorem Proving (ITP) environment, where the workload is distributed among multiple LLM-based coding agents. Rather than relying on static central planning, we implement a simulated bounty-based marketplace in which agents dynamically propose new lemmas (formal statements), attach […]
HGT-Scheduler: Deep Reinforcement Learning for the Job Shop Scheduling Problem via Heterogeneous Graph Transformers
arXiv:2603.06777v1 Announce Type: cross Abstract: The Job Shop Scheduling Problem (JSSP) is commonly formulated as a disjunctive graph in which nodes represent operations and edges encode technological precedence constraints as well as machine-sharing conflicts. Most existing reinforcement learning approaches model this graph as homogeneous, merging job-precedence and machine-contention edges into a single relation type. Such […]
Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models
arXiv:2603.06828v1 Announce Type: cross Abstract: We uncover a behavioral law of long-horizon vision-language models: models that maintain temporally grounded beliefs generalize better. Standard benchmarks measure only final-answer accuracy, which obscures how models use visual information; a model can guess correctly while its step-by-step reasoning is entirely unanchored to the visual input. We formalize this as […]
Post-Training with Policy Gradients: Optimality and the Base Model Barrier
arXiv:2603.06957v1 Announce Type: cross Abstract: We study post-training linear autoregressive models with outcome and process rewards. Given a context $boldsymbolx$, the model must predict the response $boldsymboly in Y^N$, a sequence of length $N$ that satisfies a $gamma$ margin condition, an extension of the standard separability to sequences. We prove that on test samples where […]
A Class of Unrooted Phylogenetic Networks Inspired by the Properties of Rooted Tree-Child Networks
arXiv:2603.07000v1 Announce Type: cross Abstract: A directed phylogenetic network is tree-child if every non-leaf vertex has a child that is not a reticulation. As a class of directed phylogenetic networks, tree-child networks are very useful from a computational perspective. For example, several computationally difficult problems in phylogenetics become tractable when restricted to tree-child networks. At […]
Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
arXiv:2603.07084v1 Announce Type: cross Abstract: Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often expensive or impossible to compute. We introduce Countdown-Code, a minimal environment where models can both solve a mathematical […]