SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents
- 类型：arxiv
- 标识：2610.12975
- 链接：http://arxiv.org/abs/2610.12975v1
- 主分类：evaluation
- 形态：benchmark
- TLDR：We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents against psychologically grounded, resistant buyer personas. Existing task-oriented dialogue benchmarks assume cooperative users and measure task completion; SmartSalesBench inverts this assumption, placing agents against personas programmed to resist and challenge across conversations of up to twenty turns. The benchmark includes five agent profiles, twelve buyer personas, fifteen smartphone products across six price tiers, and four controlled experi
- 副分类：agent
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-10-12-agent-rag-longcontext-candidates.json