Omar Khalil

K-halil's activity

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

upvoted 3 papers about 18 hours ago

Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries

Paper • 2610.22273 • Published 7 days ago • 10

LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets

Paper • 2610.09872 • Published 15 days ago • 134

Execution Before Memory: Diagnosing Memory Failures in Video World Models

Paper • 2610.23542 • Published 6 days ago • 34

upvoted a paper 1 day ago

OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

Paper • 2610.22200 • Published 7 days ago • 332

upvoted 2 papers 3 days ago

RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios

Paper • 2610.19698 • Published 8 days ago • 81

Hybrid Reasoning Agents

Paper • 2610.18861 • Published 9 days ago • 42

upvoted 4 papers 4 days ago

Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

Paper • 2610.12360 • Published 14 days ago • 14

DecepEval: A Benchmark for Evaluating Deception in LLM Agents

Paper • 2610.07967 • Published 16 days ago • 86

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 15 days ago • 43

CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction

Paper • 2610.16577 • Published 10 days ago • 38

upvoted 4 papers 5 days ago

ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

Paper • 2609.39306 • Published 22 days ago • 44

SparseEngine: Sparse-First Inference Engine

Paper • 2609.39068 • Published 22 days ago • 24

SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles

Paper • 2610.09832 • Published 15 days ago • 18

Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks

Paper • 2610.11794 • Published 14 days ago • 48

upvoted 2 papers 6 days ago

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 13 days ago • 119

VideoJev: System One Model for Video Understanding and Interaction

Paper • 2610.18615 • Published 9 days ago • 379

upvoted a paper 7 days ago

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published 14 days ago • 245

upvoted 3 papers 8 days ago

Stateless Language Agents: Scaling Long-Horizon Automated Research

Paper • 2610.07625 • Published 16 days ago • 31

The value of information and the emergence of communication in evolved e-puck robots

Paper • 2610.13118 • Published 13 days ago • 20

TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile Learning

Paper • 2610.10288 • Published 15 days ago • 20