Asa Cross

asacross's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 1 day ago

Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal Agents

Paper • 2608.25417 • Published 9 days ago • 17

Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities

Paper • 2608.28122 • Published 7 days ago • 65

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 3 days ago • 478

upvoted 2 papers 2 days ago

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

Paper • 2608.15763 • Published 13 days ago • 50

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Paper • 2608.27260 • Published 8 days ago • 70

upvoted a paper 3 days ago

The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents

Paper • 2608.24358 • Published 10 days ago • 14

upvoted a paper 6 days ago

Best Practice Critic Optimization

Paper • 2608.23566 • Published 10 days ago • 18

upvoted 3 papers 7 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 9 days ago • 179

ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction

Paper • 2608.13622 • Published 22 days ago • 17

MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

Paper • 2608.23035 • Published 11 days ago • 41

upvoted a paper 8 days ago

AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

Paper • 2608.20634 • Published 14 days ago • 12

upvoted a paper 9 days ago

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

Paper • 2608.20202 • Published 15 days ago • 34

upvoted 3 papers 10 days ago

Looped Language Models Improve Compositional Tool Calling

Paper • 2608.18171 • Published 18 days ago • 21

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published 16 days ago • 51

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Paper • 2608.13558 • Published 22 days ago • 92

upvoted a paper 11 days ago

ASI-Bench: At the Dawn of Artificial Superintelligence

Paper • 2608.17271 • Published 17 days ago • 64

upvoted a paper 12 days ago

Unifying Graph Neural Networks Through a Common Layer Equation

Paper • 2608.16097 • Published 18 days ago • 5

upvoted a paper 13 days ago

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published 18 days ago • 107

upvoted 2 papers 14 days ago

Agentic Transaction: Towards ACID-Compliant Agent Systems

Paper • 2608.13900 • Published 21 days ago • 27

UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations

Paper • 2608.15930 • Published 19 days ago • 47