Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and robustness evaluation, and narrow coverage of modalities and interaction paradigms. We introduce Claw-Eval, an end-to-end evaluation suite addressing these gaps with 300 human-verified tasks spanning 9 categories across three groups: general service orchestration, multimodal perception and interaction, and multi-turn professional dialogue. To enable trajectory-aware grading, each run is recorded through three independent evidence channels: execution traces, a...
| Authors | Bowen Ye, Rang Li, Qibin Yang et al. |
|---|---|
| Primary category | cs.AI |
| Published | 7 April 2026 |
| Last updated at source | 7 May 2026 |
Connected in the knowledge graph
- claw-eval/Claw-EvalDataset · cited by
Models and datasets referencing this paper
- claw-eval/Claw-EvalDataset
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 Information may be incomplete or out of date.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.