UserToolBench
Explore score history ↗UserToolBench evaluates personalized decision making in tool-use LLMs through inference of latent user preferences, clarification need, and user-aligned tool-call trajectories, built from privacy-sanitized interaction traces with 10 user profiles, 36 tool sets, and 1,065 turns.
- Released
- 2026-08-10
- Institutions
- Nanyang Technological University · Huawei Technologies (China)
- Evaluates
- General AI, Language & Knowledge, cs.LG
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
UserToolBench paper
No reported scores are on record for this benchmark yet.