Metric-Gradient Projection for Stable Multi-Agent Policy Learning
arXiv:2605.18809v1 Announce Type: cross Abstract: General-sum multi-agent learning is often governed by a stacked update field in which each agent’s…
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
arXiv:2605.18565v2 Announce Type: replace-cross Abstract: Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may…
Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
arXiv:2605.18740v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend…
KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision
arXiv:2605.19435v1 Announce Type: cross Abstract: Visual Place Recognition (VPR) is critical for autonomous navigation, yet state-of-the-art methods lack well-calibrated uncertainty…
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
arXiv:2605.15846v2 Announce Type: replace-cross Abstract: Coding agents are increasingly deployed in real software development, where a single version iteration requires…
Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect
arXiv:2605.18808v1 Announce Type: cross Abstract: We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama…
WriteSAE: Sparse Autoencoders for Recurrent State
arXiv:2605.12770v3 Announce Type: replace-cross Abstract: We introduce WriteSAE, the first sparse autoencoder that decomposes and edits the matrix cache write…
Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation
arXiv:2605.16393v1 Announce Type: cross Abstract: Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap…
$boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
arXiv:2605.17862v1 Announce Type: cross Abstract: Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution…
Overcoming the Intrinsic Performance Limitations of MEMS IMU via Diffusion-Based Generative Learning
arXiv:2605.16391v1 Announce Type: cross Abstract: Inertial measurement units (IMUs) are fundamental sensing components in multi-source integrated navigation systems, and their…