KDD

Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills

评估技能，而非仅评估智能体：智能体驱动的技能持续评估

Christopher Kevin, Narendran Raghavan, Jean-Francois Puget, Roshni Malani, Meghana Puvvadi, Moshe Abramovitch, Mohit Gupta, Rama Akkiraju, Subodh Prabhu, Yogesh Dangi, Wei Luo, Seong Hee Lee

机构 * NVIDIA（英伟达） 纠错

AI总结 该研究提出ACES框架，通过配对实际 trials等方式评估技能附加价值，实验表明其能发现扫描式审核无法观测的信号，开源实现已在NVIDIA SkillEvaluator中提供。

Comments 15 pages. Extended preprint incorporating versions accepted at Agent Skills '26 (ACM CAIS 2026) and the KDD 2026 Workshop on Enterprise AI Agents: From Prototypes to Production (oral presentation). Open-source implementation: this https URL (https://github.com/NVIDIA/SkillEvaluator)

Clarify-Then-Search: A Clarification Benchmark for Deep Search with End-to-End Nugget Restoration

先澄清再搜索：面向端到端 nugget 恢复的深度搜索澄清基准

Deqiang Huang, Jingbo Zhou, Xinjiang Lu, Tong Xu, Hua Wu, Enhong Chen

AI总结 该研究提出 Clarify-Then-Search 基准，评估 LLM 生成的澄清问题对深度搜索效用的提升，实验显示 k=1 时澄清优于基线，GPT-5.2 和 ERNIE-4.5-Turbo-128K 分别在 k=1、k=3 时表现最佳。

Comments Accepted to KDD 2026 Datasets and Benchmarks Track. 12 pages, 4 figures, 11 tables

PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval

PhotoBench: 超越视觉匹配，迈向个性化意图驱动的图片检索

Tianyi Xu, Rong Shan, Junjie Wu, Jiadeng Huang, Teng Wang, Jiachen Zhu, Wenteng Chen, Minxin Tu, Quantao Dou, Zhaoxiang Wang, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

AI总结 PhotoBench 是首个基于真实个人相册构建的基准，旨在通过多源意图驱动推理提升个性化图片检索能力。

Comments Accepted by KDD'26 Benchmark track