…🧩 Routing policy learning : from heuristic to LLM-selection, classifier-based, RL-based, to self-routing 🛠️ Cooperative capability learning : agents trained in isolation against fixed partners fail to generalize; genuine cooperation…
…Crucially, we demonstrate that the depth and width of heavy thinking, as a learnable skill, can be further scaled via reinforcement learning , offering a promising path toward self-evolving LLMs that internalize…
…At the core of Track2View is a dual-view track conditioner that transfers visual context from source to target view through parameter-free geometric operations and learned temporal aggregation , ensuring generalization to…
…are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation…
…While memory mechanisms have emerged as the architectural cornerstone of these systems, current research remains fragmented, oscillating between operating system engineering and cognitive science. This theoretical divide prevents a unified view of…
…Xuhao Hu , , Haiyang Xu , , Jingyi Yang , , , , Abstract ToolCUA is an end-to-end agent that learns optimal GUI-tool path selection through staged training, achieving superior performance in hybrid action space environments…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct As deep learning models scale, managing, inspecting, and modifying large checkpoints has become increasingly challenging. Researchers often need to alter model weights for layer…
…To probe this challenge, we introduce PaintBench, a dynamically scalable benchmark targeting 20 fundamental precise visual editing operations across four categories: geometric transformation, structural manipulation, color change, and symbolic reasoning. Procedural generation…
…These features are causally operative: they survive the K/V attention projections , trace to the FFN neuron coalitions that write them (random-weight controls never reproduce this), and flipping a feature's…
…Finally, a diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images. Through large-scale pre-training, followed by supervised fine-tuning and reinforcement learning , UniAR achieves state…