Darrow O'Lykos

darrowoflykos's activity

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

upvoted 10 papers about 7 hours ago

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

Paper • 2606.09426 • Published Jun 8 • 50

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

Paper • 2606.02031 • Published Jun 1 • 21

OpenForgeRL: Train Harness-native Agents in Any Environment

Paper • 2607.21557 • Published Jul 23 • 13

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

Paper • 2608.00155 • Published Jul 31 • 21

XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding

Paper • 2608.00036 • Published Jul 21 • 3

ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog

Paper • 2607.04438 • Published Jul 5 • 62

ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes

Paper • 2607.04439 • Published Jul 5 • 64

HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents

Paper • 2606.31179 • Published Jun 30 • 7

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Paper • 2608.23041 • Published Aug 24 • 66

Sliding-window beats linear attention

Paper • 2608.28444 • Published Aug 28 • 19

upvoted 10 papers about 9 hours ago

CUAWright: A Minimal Unified Interface for Digital Agents

Paper • 2610.04116 • Published 6 days ago • 5

Can Computation from Earlier Problems Help LLMs Solve New Ones?

Paper • 2609.39394 • Published 8 days ago • 9

Octrees as an Explicit 3D Language

Paper • 2610.02388 • Published 7 days ago • 15

Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability

Paper • 2610.03509 • Published 6 days ago • 15

Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers

Paper • 2608.26762 • Published 12 days ago • 22

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

Paper • 2610.03715 • Published 6 days ago • 29

TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization

Paper • 2605.21318 • Published 3 days ago • 8

What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

Paper • 2610.04128 • Published 6 days ago • 9

MM-ABC: Towards Generalist Mobile Manipulation via Seeing, Coordinating and Imagining

Paper • 2609.35652 • Published 10 days ago • 6

DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents

Paper • 2610.02320 • Published 7 days ago • 11