AI Agent Papers2026
Shuang Sun, Guoxin Chen +7Affiliation: Gaoling School of Artificial Intelligence, Renmin University of China
Edits an LLM agent's internal task state and action continuations to remove unsupported assumptions and noisy plans, improving downstream decisions instead of reconstructing high-entropy tool outputs. Combines Action Judge, State Revision, and EditAct and shows consistent gains across benchmarks and agent backbones.