arXiv
Verdict: NotableCoworkOS:Scaling Agent Coworkers for Real-world Automation
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts.
- HF ▲ 89
- Stars ★ 78
Artificial Intelligence
Models, methods, and the machinery of intelligence.
Edition No. 37
Updated UTC
Top stories
1. PhotoGuider: Composition-Aware Cropping and 360^° View Framing with Explainable Photographic Assessments
Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop.
Verdict: Notable█████░░░░░5.22. Measuring AI Agents as Teammates with Collaborative Intelligence
Progress in AI is often measured by what a single model can do on its own.
Verdict: Notable█████░░░░░4.6
More top stories
- arXivby Hu, Wang, Talwar +3
DR Pixel: Page-Native Deep Research with Vision-Language Models
Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to ....
No.03Verdict: NotableScore████░░░░░░4.5 - arXivby Zhao, Zhang, Li
Can Coding Agents Sustain Continual Evolution without Forgetting?
Recently, harness self-evolution has emerged as an important paradigm for improving agent performance.
No.04Verdict: NotableScore████░░░░░░4.2 - arXivby Wu, Huang, Ho +3
RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory
Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm ....
No.05Verdict: NotableScore████░░░░░░4.2 - arXivby Maser, Gairola, Rao +1
Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers
Foundational vision models have become the de facto standard for many vision tasks due to their strong performance.
No.06Verdict: NotableScore████░░░░░░4.1 - arXivby Fishman, Sun, Acharya +6
Dory1.0-4B: A Looped Normalized-GPT
We introduce Dory1.0-4B, a 4-billion-parameter looped (latent-recurrent) language model with elastic depth: a single checkpoint serves different inference compute budgets.
No.07Verdict: NotableScore████░░░░░░4.0 - arXivby Dick, Lonsway
ExaTune: Exhaustive Hyperparameter Landscape Exploration at Scale
Hyperparameter optimization (HPO) returns a single optimal configuration, systematically discarding the explored performance landscape that encodes how results depend on configuration ....
No.08Verdict: NotableScore████░░░░░░4.0
Briefs
- arXiv
DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
████░░░░░░3.9 - arXiv
Say Less, Mean Better: Training-Free Verbosity Control for Language Models
████░░░░░░3.9 - arXiv
SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
████░░░░░░3.9 - arXiv
Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
████░░░░░░3.9 - arXiv
KlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RL
████░░░░░░3.9 - arXiv
RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild
████░░░░░░3.9 - arXiv
TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation
████░░░░░░3.9 - arXiv
VLM-as-a-Judge for Person Re-Identification
████░░░░░░3.9 - arXiv
MirrorComm: A Communication-Efficient Cooperative Perception Framework via Mirrored World Models
████░░░░░░3.9 - arXiv
Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters
████░░░░░░3.8