Papers2

#Group Relative Policy Optimization (GRPO)

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training

The paper introduces Rubric-ARM, a system that teaches two AI helpers—a rubric maker and a judge—to learn together using reinforcement learning so they can better decide which answers people would prefer.

#Rubric-based reward modeling#LLM-as-a-judge#Alternating reinforcement learning

GameTalk: Training LLMs for Strategic Conversation

Intermediate

Victor Conchello Vendrell, Max Ruiz Luyten et al.Jan 22arXiv

Large language models usually get judged one message at a time, but many real tasks need smart planning across a whole conversation.

#strategic conversation#reinforcement learning for LLMs#multi-turn dialogue