SecurityWeek

PyPI Warns Users of Fresh Phishing Campaign

PyPI, the default platform for Python's package management tools, is warning users of a fresh phishing campaign.
GitHub

uqlm: Uncertainty Quantification for Language Models

UQLM provides a suite of response-level scorers for quantifying the uncertainty of Large Language Model (LLM) outputs. Each scorer returns a confidence score between 0 and 1, where higher scores ...
IEEE

Real-Time Scheduling for Flexible Job Shop With AGVs Using Multiagent Reinforcement Learning and Efficient Action Decoding

Abstract: The application of automated guided vehicle (AGV) greatly improves the production efficiency of workshop. However, machine flexibility and limited logistics equipment increase the complexity ...
GitHub

Train multi-step agents for real-world tasks using GRPO.

RULER (Relative Universal LLM-Elicited Rewards) eliminates the need for hand-crafted reward functions by using an LLM-as-judge to automatically score agent trajectories. Simply define your task in the ...