GPBam: A Retrieval-Aware German Public Law Exam Benchmark Paper • 2611.18981 • Published 6 days ago • 2 • 3
Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns Paper • 2611.19244 • Published 5 days ago • 8 • 6
Self-Improvement Memory Enables Continual Recursive Self-Improvement Paper • 2611.18856 • Published 6 days ago • 32 • 6
Do LLM Agents Still Need to Be Told How to Self-Improve? Paper • 2611.23219 • Published 2 days ago • 6 • 3
Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior Paper • 2611.04395 • Published 16 days ago • 5 • 3
The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision models Paper • 2611.15671 • Published 8 days ago • 5 • 5
LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting Paper • 2611.11912 • Published 10 days ago • 2 • 8
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription Paper • 2611.06043 • Published 15 days ago • 72 • 9
Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game Paper • 2611.14487 • Published 9 days ago • 10 • 3
SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations Paper • 2611.20218 • Published 4 days ago • 52 • 4
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription Paper • 2611.06043 • Published 15 days ago • 72 • 9
Continual-ARC: Measuring Skill Acquisition over a Working Lifetime Paper • 2611.14505 • Published 8 days ago • 3 • 6
SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models Paper • 2611.15777 • Published 8 days ago • 73 • 5
Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery Paper • 2611.12762 • Published 10 days ago • 61 • 7
Continual-ARC: Measuring Skill Acquisition over a Working Lifetime Paper • 2611.14505 • Published 8 days ago • 3 • 6
Interpreting Coding Agents Through Their Behavioral Trajectories Paper • 2611.17440 • Published 7 days ago • 11 • 4
The Value of Thinking: Learning When to Reason in Hybrid Decision Models Paper • 2611.16961 • Published 7 days ago • 9 • 13