Issue 105
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-q...
Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lac...
Multimodal large language models (MLLMs) can generate detailed video captions, yet they may overemphasize minor details while overlooking essential context and key events. We argue that not all visual...
Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop. A full 360^{circ} scene offers no such guarantee: the viewing direction i...
Personal AI agents are increasingly capable of handling long-horizon tasks across applications, yet users often need to invest substantial effort in specifying goals, resolving ambiguity, and verifyin...
Long-horizon tasks require large language model (LLM) agents to coordinate interdependent actions, a capability central to automating complex workflows. Stepwise group-based reinforcement learning pro...
TLAPS-Bench is a benchmark and execution harness for constructing machine-checked proofs for real-world system specifications in TLA+ with agentic AI. Proving correctness of complex system specificati...
LLM agents are increasingly built into data-analysis software, yet little evidence shows how reliably they preprocess clinical data or whether the tools they invoke give correct, reproducible output. ...
Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality. Extending them to joint quality--cost optimization ...
Attention remains a substantial computational cost in Transformer training, particularly at long context lengths. NVIDIA Blackwell GPUs provide high-throughput low-precision matrix multiplication, but...