arXiv:2508.00890v2 Announce Type: replace Abstract: Test-time scaling (TTS) enhances the performance of large language models (LLMs) by allocating additional compute resources during inference. However, existing research primarily investigates TTS in single-stage tasks; while many real-world problems are multi-stage complex tasks, composed of a sequence of heterogeneous subtasks with each subtask requires LLM of specific capability. […]
SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes
arXiv:2510.19241v1 Announce Type: cross Abstract: Interpretable reinforcement learning policies are essential for high-stakes decision-making, yet optimizing decision tree policies in Markov Decision Processes (MDPs) remains challenging. We propose SPOT, a novel method for computing decision tree policies, which formulates the optimization problem as a mixed-integer linear program (MILP). To enhance efficiency, we employ a reduced-space […]
Continual Knowledge Adaptation for Reinforcement Learning
arXiv:2510.19314v1 Announce Type: new Abstract: Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks and changing conditions. Although Continual Reinforcement Learning facilitates learning across multiple tasks, existing methods often suffer from catastrophic forgetting and inefficient knowledge utilization. To […]
Social World Model-Augmented Mechanism Design Policy Learning
arXiv:2510.19270v1 Announce Type: cross Abstract: Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits (e.g., skills, preferences) and dealing with complex multi-agent system dynamics. These challenges are compounded by the critical need for high sample […]
The Right to Be Remembered: Preserving Maximally Truthful Digital Memory in the Age of AI
arXiv:2510.16206v2 Announce Type: replace Abstract: Since the rapid expansion of large language models (LLMs), people have begun to rely on them for information retrieval. While traditional search engines display ranked lists of sources shaped by search engine optimization (SEO), advertising, and personalization, LLMs typically provide a synthesized response that feels singular and authoritative. While both […]
Online Handwritten Signature Verification Based on Temporal-Spatial Graph Attention Transformer
arXiv:2510.19321v1 Announce Type: cross Abstract: Handwritten signature verification is a crucial aspect of identity authentication, with applications in various domains such as finance and e-commerce. However, achieving high accuracy in signature verification remains challenging due to intra-user variability and the risk of forgery. This paper introduces a novel approach for dynamic signature verification: the Temporal-Spatial […]
MSC-Bench: A Rigorous Benchmark for Multi-Server Tool Orchestration
arXiv:2510.19423v1 Announce Type: new Abstract: We introduce MSC-Bench, a large-scale benchmark for evaluating multi-hop, end-to-end tool orchestration by LLM agents in a hierarchical Model-Context Protocol (MCP) ecosystem. Existing benchmarks often evaluate tools in isolation, ignoring challenges such as functional overlap and cross-server orchestration, leading to overly optimistic assessments. MSC-Bench addresses these gaps by constructing ground […]
Seabed-Net: A multi-task network for joint bathymetry estimation and seabed classification from remote sensing imagery in shallow waters
arXiv:2510.19329v1 Announce Type: cross Abstract: Accurate, detailed, and regularly updated bathymetry, coupled with complex semantic content, is essential for under-mapped shallow-water environments facing increasing climatological and anthropogenic pressures. However, existing approaches that derive either depth or seabed classes from remote sensing imagery treat these tasks in isolation, forfeiting the mutual benefits of their interaction and […]
Open-World Drone Active Tracking with Goal-Centered Rewards
arXiv:2412.00744v2 Announce Type: replace-cross Abstract: Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations, providing a more practical solution for effective tracking in dynamic environments. However, accurate Drone Visual Active Tracking using reinforcement learning remains challenging due to the absence of a unified benchmark […]
Foundation Model Forecasts: Form and Function
arXiv:2510.19345v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) achieve strong forecast accuracy, yet accuracy alone does not determine practical value. The form of a forecast — point, quantile, parametric, or trajectory ensemble — fundamentally constrains which operational tasks it can support. We survey recent TSFMs and find that two-thirds produce only point or parametric […]