AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for evaluation without human involvement. Despite their flexibility, their reliability on long tasks spanning multiple applications remains unclear. A trajectory, composed of long sequences of screenshots and actions, may appear complete, but in reality violates constraints from the instruction or introduces an unwanted side effect. To identify these errors, a judge needs to examine the trajectory with respect to the user's instruction. To this end, we introduce AgentHorizon, a benchmark of 1,373 computer-use tasks (instruction-trajectory pairs) ...
| Authors | Xing Han Lù, Dheeraj Vattikonda, Sina Hajimiri et al. |
|---|---|
| Primary category | cs.AI |
| Published | 8 October 2026 |
| Last updated at source | 8 October 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- ServiceNow/AgentHorizonDataset · cited by
Models and datasets referencing this paper
- ServiceNow/AgentHorizonDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.