Pinned Loading

1. DyPRAG DyPRAG Public

   [arxiv: 2503.23895] Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement

   Python 185 19

2. BuPO BuPO Public

   [EMNLP 2026 Main] Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

   Python 60 6

3. Pretrain_Space_RLVR Pretrain_Space_RLVR Public

   [arxiv: 2604.14142] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space

   Python 17

4. SWE-Touch SWE-Touch Public

   [arxiv:2608.02499] SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

   Python 15

5. posttrainbench0 posttrainbench0 Public

   [Blog] PostTrainBench⁰ — Can LLM agents automate LLM post-training without gradients?

   Python 14

6. SAEScientist SAEScientist Public

   [arxiv:2609.09113] SAEScientist-Bench: Can AI agents conduct autonomous SAE interpretability research?

   Python 17