aiqbench analysis
This arXiv paper proposes SPAR, an LLM-based sales agent framework that treats selling strategies as testable hypotheses and updates them without changing model parameters. Its double-loop design separates per-merchant adaptation from a shared strategy playbook, and it uses causal attribution to tell flawed strategies apart from external factors. The reported gains (+15.8% conversion in a live A/B test on 1688 with over 200,000 merchants) are from a single platform, so readers should check how the evaluation controlled for confounders before generalizing.
SPAR: Experience-Driven Strategy Evolution in Multi-Session B2B Sales
arXiv:2611.01695v1 Announce Type: new Abstract: B2B outbound sales involves high transaction values and relationship-based trust, so closing a deal typically requires multiple rounds of outreach building on prior context. Existing LLM-based sales agents operate within single sessions and cannot carry forward context or refine strategies from experience. Methods that do learn from experience store lessons as unstructured text and treat all outcomes as equally informative, with no mechanism to distinguish a flawed strategy from an external factor. We propose SPAR, a self-evolving framework that models selling strategies as testable hypotheses and refines them without parameter updates. A double-loop architecture lets an inner loop adapt to individual merchants through episodic memory while an outer loop evolves a shared strategy playbook through causal attribution and hypothesis-driven evolution. In a live A/B test on the 1688 platform with over 200,000 merchants, SPAR achieves +15.8% conversion lift and +35.8% high-intent merchant growth. Human evaluation by domain experts rates SPAR at 4.62 out of 5 on overall sales quality, the highest among all methods.
Read the full article at arXiv