arXiv 2510.182892026-06-11cs.CLcs.CYcs.MA

Food4All: 一种具有自适应用户理解能力的食物资源导航智能体框架与基准

Food4All: An Agentic Framework and Benchmark for Food Resource Navigation with Adaptive User Understanding

University of Notre Dame（诺特大学）

Yiyang Li, Weixiang Sun, Tianyi Ma, Kaiwen Shi, Zheyuan Zhang, Yanfang Ye

备注：: We have further refined the benchmark construction and experimental presentation to improve clarity and consistency. The revised version includes updated task design, food-resource data, and evaluation details to better align the benchmark with the intended food resource referral setting. These changes provide a more precise presentation of the experimental findings

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出Food4All框架，结合食物搜索工具与300个多轮评估任务，在686个印第安纳食物资源上评估六种大语言模型，诊断其在约束条件处理和非理想用户交互中的不足。

摘要：

食物援助推荐需要对话智能体将未明确指定且常含噪声的求助对话转化为本地有效的资源推荐。我们提出Food4All，一个基于686个结构化印第安纳食物资源的智能体食物资源推荐框架与基准。Food4All将食物特定搜索工具与300个多轮评估任务相结合，涵盖单一食物需求、具有访问或文件约束的复合案例，以及五种非理想用户交互特征：不合理要求、冗长回答、不耐烦、不完整答案和不一致信息。我们在需求理解、资源检索、最终推荐正确性和交互效率上评估了六种大语言模型。尽管最强模型达到了96.33%的推荐准确率，但我们的诊断揭示了在时间安排、资格、接收和文件约束方面的持续失败，以及在最终推荐中未能保留有效检索到的资源。特征级分析进一步表明，不同的非理想行为对推荐流程的不同部分造成压力。Food4All为在现实用户交互挑战下研究约束敏感的食物援助推荐中的工具调用智能体提供了一个受控测试平台。

英文摘要：

Food assistance referral requires conversational agents to translate underspecified, often noisy help-seeking dialogues into locally valid resource recommendations. We present Food4All, an agentic food-resource referral framework and benchmark grounded in 686 structured Indiana food resources. Food4All couples a food-specific search tool with 300 multi-turn evaluation tasks spanning single food needs, composite cases with access or document constraints, and five non-ideal user interaction traits: unreasonable demands, rambling responses, impatience, incomplete answers, and inconsistent information. We evaluate six Large Language Models (LLMs) on requirement grounding, resource retrieval, final referral correctness, and interaction efficiency. Although the strongest model achieves 96.33% referral accuracy, our diagnostics reveal persistent failures in grounding schedule, eligibility, intake, and document constraints, as well as failures to preserve valid retrieved resources in the final recommendation. Trait-level analysis further shows that different non-ideal behaviors stress different parts of the referral pipeline. Food4All provides a controlled testbed for studying tool-calling agents in constraint-sensitive food assistance referral under realistic user interaction challenges.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。