一作ACL 2026Poster· Natural Language Processing
PRI n TS : Reward Modeling for Long-Horizon Information Seeking
Jaewoo Lee · Archiki Prasad · Justin Chen · Zaid Khan · Elias Stengel-Eskin · Mohit Bansal
摘要
Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by language models. While process reward models (PRMs) can...