All news

2 articles

Min score

paperarXiv (systems, data, ML)·22 Oct 20263.2
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
Reward models for when LLM assistants should use memory.
agent-memory reward-modeling
paperarXiv (systems, data, ML)·22 Oct 20263.1
What Pairwise Evaluation Misses: Reward Scores across Prompts
Shows reward model scores are not comparable across prompts.
reward-modeling