Given the limitations of existing fine-tuning techniques such as GRPO, GVPO has emerged as a reliable and versatile post-training paradigm.
AEPO focuses on balancing and rationalizing strategy extension branches and strategy updates under the guidance of high-entropy tool calls.
HiPO is used for adaptive LLM inference, mainly including hybrid data construction and hybrid reinforcement learning.
ReinFlow features a lightweight implementation, built-in exploration capabilities, and broad applicability to various streaming strategy variants.
ACE enables agents to improve themselves by dynamically optimizing the input context.
The model approximates the Gödel Machine in a coding agent environment and guides the expansion through Thompson sampling with adaptive scheduling.
SSP demonstrates the potential of self-game theory as a scalable and data-efficient training paradigm for agent LLM.
CudaForge is a simple, effective, and low-cost multi-agent workflow for CUDA kernel generation and optimization.
Given the limitations of existing fine-tuning techniques such as GRPO, GVPO has emerged as a reliable and versatile post-training paradigm.
AEPO focuses on balancing and rationalizing strategy extension branches and strategy updates under the guidance of high-entropy tool calls.
HiPO is used for adaptive LLM inference, mainly including hybrid data construction and hybrid reinforcement learning.
ReinFlow features a lightweight implementation, built-in exploration capabilities, and broad applicability to various streaming strategy variants.
ACE enables agents to improve themselves by dynamically optimizing the input context.
The model approximates the Gödel Machine in a coding agent environment and guides the expansion through Thompson sampling with adaptive scheduling.
SSP demonstrates the potential of self-game theory as a scalable and data-efficient training paradigm for agent LLM.
CudaForge is a simple, effective, and low-cost multi-agent workflow for CUDA kernel generation and optimization.