τ-Rec Benchmark
Explore score history ↗A benchmark for multi-turn agentic recommender systems that exposes dialogue constraints through reveal-tagged elicitation and verifies outcomes against structured catalog predicates.
- Released
- 2026-06-08
- Institutions
- Princeton University
- Evaluates
- General AI, Language & Knowledge, cs.IR
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
τ-Rec paper and code
No reported scores are on record for this benchmark yet.