Multi-Agent System Process Reward Model (MASPRM): a lightweight process reward model guiding multi-agent systems at search time.
-
Updated
Jul 14, 2026 - Python
#
inference-time-reasoning
Here are 2 public repositories matching this topic...
Tasked with building a general-purpose reasoning agent capable of solving arbitrary problem-solving tasks that decides dynamically on its own to use of nine unique inference-time algorithms best for the problem. We only used the provided ASU Research Compute (SOL) LLM API required.
-
Updated
Apr 28, 2026 - Python
Improve this page
Add a description, image, and links to the inference-time-reasoning topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the inference-time-reasoning topic, visit your repo's landing page and select "manage topics."