Pinned Loading

1. InstructRAG InstructRAG Public

   [ICLR 2025] InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

   Python 152 9

2. AdaDecode AdaDecode Public

   [ICML 2025] AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

   Python 20 2

3. WebAgent-R1 WebAgent-R1 Public

   [EMNLP 2025] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

   Python 100 5

4. facebookresearch/TruthRL facebookresearch/TruthRL Public

   TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

   Python 21 11

5. RELEX RELEX Public

   [NeurIPS 2026] You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

   Python 19 2

6. MSR-Orchard/Self-HPO MSR-Orchard/Self-HPO Public

   Self-HPO: self-improving harness + policy co-optimization for agentic SWE

   Python 53 4