Xin Eric Wang

xw-eric's activity

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

authored 7 papers 6 days ago

Evolving Agent Interfaces

Paper • 2610.28601 • Published 7 days ago • 23

LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents

Paper • 2610.22280 • Published 12 days ago • 13

MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization

Paper • 2609.36435 • Published 28 days ago • 8

Multi-Agent LLMs Fail to Explore Each Other

Paper • 2607.11250 • Published Jul 13 • 15

Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA

Paper • 2405.20421 • Published May 30, 2024

OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Paper • 2606.29537 • Published Jun 28 • 25

WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction

Paper • 2605.29341 • Published May 28 • 14

upvoted a paper 6 days ago

Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey

Paper • 2602.06052 • Published Jan 14 • 8

liked a dataset 6 days ago

simular-ai/evolving_agent_interfaces_synthetic_tasks

Updated 5 days ago • 88 • 1

upvoted a paper 6 days ago

Evolving Agent Interfaces

Paper • 2610.28601 • Published 7 days ago • 23

liked a dataset 5 months ago

LCZZZZ/WorldMemArena

Viewer • Updated May 20 • 15.6k • 6.04k • 3

upvoted a paper 5 months ago

WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction

Paper • 2605.29341 • Published May 28 • 14

authored a paper 5 months ago

Auditing Agent Harness Safety

Paper • 2605.14271 • Published May 14 • 55

upvoted a paper 5 months ago

Auditing Agent Harness Safety

Paper • 2605.14271 • Published May 14 • 55

authored 2 papers 6 months ago

SafePro: Evaluating the Safety of Professional-Level AI Agents

Paper • 2601.06663 • Published Jan 13

Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling

Paper • 2604.27039 • Published Apr 29 • 25

upvoted a paper 6 months ago

Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling

Paper • 2604.27039 • Published Apr 29 • 25

authored 3 papers 6 months ago

Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space

Paper • 2512.12623 • Published Dec 14, 2025 • 4

Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey

Paper • 2602.06052 • Published Jan 14 • 8

Context Bootstrapped Reinforcement Learning

Paper • 2603.18953 • Published Mar 19