Pinned Loading

1. Agentic-ESOpt Agentic-ESOpt Public

   Code for Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

   Python 32 3

2. SofT-GRPO-master SofT-GRPO-master Public

   Code for the SofT-GRPO algorithm on the LLM soft-thinking reasoning pattern.

   Python 52 3

3. CIAM-Group/NCO_code CIAM-Group/NCO_code Public

   L2O/NCO codes from CIAM Group at SUSTech, Shenzhen, China

   Python 100 27

4. MCTS-AHD-master MCTS-AHD-master Public

   Code for [ICML2025]``Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design``.

   Python 84 18

5. ATP-Latent-master ATP-Latent-master Public

   Python 17 2

6. Latent-Memory-Master Latent-Memory-Master Public

   Code Implementation for Paper: "One Token per Multimodel Evidence: Latent Memory for Resource-Constrained QA"

   Python 9