PAPER·May 26, 2026Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary EnhancementarXiv
TECH·May 22, 2026CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs | Hacker NewsHacker News
PAPER·May 22, 2026Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement LearningHugging Face Papers
PAPER·May 21, 2026Mem-π: Adaptive Memory through Learning When and What to GenerateHugging Face Papers
PAPER·May 20, 2026Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon AgentsarXiv
PAPER·May 15, 2026STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?Hugging Face Papers
