τ-Rec:面向智能体型推荐系统的可验证基准
阅读原文· arxiv.orgτ-Rec 是一个面向智能体型推荐系统的评估基准,用可验证奖励和 reveal-tagged elicitation(RTE)机制替代主观的 LLM-as-a-judge 评估。该基准通过结构化目录谓词测试智能体,并采用 pass^k 可靠性指标衡量一致性推理。对五个模型族(GPT-5.4、Claude Sonnet 4.6、Gemini 2.5 Flash、DeepSeek V4 Flash、Qwen3-32B 和 GPT-5 mini)的九种配置评估发现显著的可靠性悬崖:最佳模型在 pass^1 上仅约 57%,在 pass^4 上降至约 38%,暴露出当前对话智能体部署中的关键差距。全部代码和数据已公开。
As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benchmarks often rely on "LLM-as-a-judge" evaluations, which introduce subjectivity, high costs and inconsistency. We present τ-Rec, a benchmark for agentic recommender systems that replaces subjective evaluation with verifiable rewards and a reveal-tagged elicitation (RTE) mechanism that controls how task constraints surface during dialogue. By testing agents against structured catalog predicates and employing a pass^k reliability metric, τ-Rec provides a systematic test for consistent reasoning. Our evaluation of nine configurations across five model families -- GPT-5.4, Claude Sonnet 4.6, Gemini 2.5 Flash, DeepSeek V4 Flash, Qwen3-32B and GPT-5 mini -- reveals a steep reliability cliff, where even the best model achieves only ~57% at pass^1 and ~38% at pass^4, highlighting a critical gap in current conversational agent deployment. All code and data are publicly available at https://github.com/nbharaths/tau-rec.