RESEARCHInvestigateNEXT 12 MONTHS
The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
A systematic survey of 1,547 papers defines the 'horizon gap' where LLM agents fail at multi-hour tasks due to memory and planning drift.
Open source