PRInTS: Reward Modeling for Long-Horizon Information Seeking
Researchers have developed PRInTS, a new generative reward model designed to improve AI agents' ability to seek information over long periods. Unlike previous models that offered binary judgments on short tasks, PRInTS provides dense, multi-dimensional scoring for each step, considering factors like tool interpretation and output informativeness. It also compresses long contexts into summaries while retaining essential information for evaluation. Experiments on benchmarks like FRAMES and GAIA show that PRInTS significantly enhances information-seeking capabilities in various agents, even outperforming larger, frontier models. AI
IMPACT Enhances AI agent capabilities in complex, multi-step information gathering, potentially improving performance in tasks requiring extensive tool use and reasoning.