What’s Happening in My Field

Recent arXiv papers in RL post-training · reasoning · self-improvement · multimodal LLMs
Auto-updated weekly via GitHub Actions · Last update: 2026-07-27
Self-Improvement
CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference
Jiyuan Tan, Vasilis Syrgkanis
2026-07-24
 Audio Reasoning
Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning
Siqian Tong, Xuan Li, Chaozhuo Li et al.
2026-07-22
 Self-Improvement
Knowledge-Centric Self-Improvement
Xuefei Julie Wang, Lauren Hyoseo Yoon, Chengrui Qu et al.
2026-07-21
 RL Training
Verifiable Self-Evolution for Open-Ended Dialogue Skills via Future-Feedback Prediction
ChaoJin Zhao, Xuan Jiang
2026-07-21
 Self-Improvement
A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification
Bogdan Raduta, Horia Velicu, Alexandru Preda et al.
2026-07-20
 Self-Improvement
Recursive Harness Self-Improvement
Hyunin Lee, Jinglue Xu, Jeffrey Seely et al.
2026-07-17
 Reasoning
Process Reward Informed Tree Rollout for Effective Multi-Turn RL
Xintong Li, Sha Li, Yuwei Zhang et al.
2026-07-17
 RL Training
Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback
Patrick Wilhelm, Odej Kao
2026-07-15
 Reasoning
LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning
Qiang Zhu, Jiajun Wu, Longyi Wang
2026-07-15

← Back to homepage