LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation
Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing benchmarks often center on localized tasks or end-state outcomes, offering limited insight into sustained execution. We introduce LOOPSBENCH, a long-horizon benchmark for loop engineering in coding agent evaluation. Each task is a dependency DAG over separately testable development units with source-evidenced prerequisite edges. LOOPSBENCH comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains. Its flow-aware runtime releases tests along the ready frontier and retains completed no...
| Authors | Han Li, Zhemin Fang, Rili Feng et al. |
|---|---|
| Primary category | cs.SE |
| Published | 31 July 2026 |
| Last updated at source | 10 August 2026 |
Connected in the knowledge graph
- LoopsBench/LoopsBenchDataset · cited by
Models and datasets referencing this paper
- LoopsBench/LoopsBenchDataset
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 Information may be incomplete or out of date.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.