Benchmark RadarAI BENCHMARK PROFILE
ComboShoppingBench
ComboShoppingBench is a benchmark for agentic basket shopping with coupons, evaluating LLM agents on constructing feasible baskets with budget and coupon constraints in a simulated environment.
- Released
- 2026-08-10
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
It addresses the gap in evaluating agents for combinatorial shopping tasks, which require joint reasoning about compatibility, availability, and constraints.
Motivation
Real-world shopping often requires constructing a basket of complementary items rather than retrieving a single product.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.