Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Paper • 2609.05571 • Published • 92
🔄 In a Training Loop
Urro
urroxyz
AI & ML interests
computational linguistics major 🤖🔎ðŸ”
i am autistic. if i come off rude, i probably didn't mean to. please feel free to ask me for clarification.
Recent Activity
upvoted a paper about 20 hours ago
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence upvoted a paper about 20 hours ago
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself updated a collection about 20 hours ago
WTF GENIUS PAPERSOrganizations
upvoted 4
papers about 20 hours ago
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Paper • 2609.22068 • Published • 104
MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
Paper • 2609.15126 • Published • 7
Calibrating Teacher--Student Discrepancy for On-Policy Distillation
Paper • 2609.21619 • Published • 7
upvoted 3
papers 3 days ago
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
Paper • 2609.19499 • Published • 30
Verifiable Social Reasoning for LLM Assistants
Paper • 2609.17496 • Published • 54
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Paper • 2609.20715 • Published • 33
upvoted 6
papers 4 days ago
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Paper • 2609.20519 • Published • 106
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation
Paper • 2609.20511 • Published • 104
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Paper • 2609.19969 • Published • 159
What Does Privileged Information Add to On-Policy Self-Distillation?
Paper • 2609.20612 • Published • 31
When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models
Paper • 2609.19671 • Published • 41
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2609.20784 • Published • 46
upvoted 7
papers 5 days ago
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Paper • 2609.06986 • Published • 370
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Paper • 2609.16816 • Published • 11
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation
Paper • 2609.13770 • Published • 9
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
Paper • 2609.17488 • Published • 591
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization
Paper • 2609.14320 • Published • 33
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Paper • 2609.18708 • Published • 75
Register Tokens for Bounded-State Reasoning in Diffusion Language Models
Paper • 2609.16372 • Published • 7