Preprint
Aug 2026
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
This work reformulate long-horizon execution as a task-state management problem and proposes LongHorizon-Harness, which maintains the task state explicitly outside execution and updates it only with facts independently verified from the environment.
Ziyu Ma, Hailang Huang, Shun Zou et al.
· 2 citations