Self-Improving-Coding-Agents/SI2CA-Training-Trajectories
Viewer • Updated • 43.1k • 345
AI & ML interests
Self-improving coding agents, recursive self-improvement, agentic reasoning, trajectory curation, and model distillation.
Recent Activity
View all activity
MasterVito
published a
dataset 15 days ago
MasterVito
updated a
dataset 15 days ago
MasterVito
updated a
Space 15 days ago
MasterVito
published a
Space 15 days ago
MasterVito
authored a
paper 8 months ago
MasterVito
submitted a
paper to Daily Papers 8 months ago
MasterVito
authored a
paper 9 months ago
MasterVito
authored a
paper 10 months ago
MasterVito
authored 2
papers about 1 year ago
MasterVito
authored 3
papers over 1 year ago
TL;DR: Too Long, Do Re-weighting for Effcient LLM Reasoning Compression
Paper • 2506.02678 • Published • 5
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Paper • 2506.14245 • Published • 45
SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
Paper • 2506.08989 • Published • 14