AuXSpec: Learning to Autoformalize Program Specifications via Executable Postconditions Paper • 2611.21421 • Published 4 days ago • 5
VisualArtifactSpec 1.0: Evaluating Visual Artifacts under Task Specifications Paper • 2611.21382 • Published 4 days ago • 8
CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference Paper • 2611.22563 • Published 3 days ago • 11
From Repositories to Training Environments: Scaling Long-Horizon Coding Agents with Environment Evolution Loop Paper • 2611.21152 • Published 3 days ago • 15
Self-Improvement Memory Enables Continual Recursive Self-Improvement Paper • 2611.18856 • Published 7 days ago • 34
TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks Paper • 2611.22115 • Published 3 days ago • 163
DrawScore: Evaluating Generated CAD Models against Engineering Drawings Paper • 2611.24681 • Published 2 days ago • 5
NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding Paper • 2611.22790 • Published 3 days ago • 4
Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow Paper • 2611.23751 • Published 2 days ago • 13
Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement Paper • 2611.24651 • Published 2 days ago • 12
The Resolution Hypothesis: Agent Evolution's Key Is Identifying Improvements Paper • 2611.23068 • Published 3 days ago • 36
view article Article Bring Your Own Expert! Extending MoE Models with New Domain Expertise tngtech • 10 days ago • 13
view article Article How we optimized our workflows and overcame GitHub Actions limitations ggml-org • 4 days ago • 7