English(EN) Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels

新的ZEST-Search框架在无标签情况下训练高效AI搜索代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-29 09:28

研究人员开发了ZEST-Search，一个新颖的深度搜索代理训练框架，可在无需标注数据的情况下提高答案准确性和工具效率。该方法采用异构协同进化方法，其中自适应提议器围绕求解器的当前能力构建训练任务，而求解器则学习与外部检索进行推理。ZEST-Search包含中等难度和工具感知奖励，以鼓励信息性任务并最大限度地减少冗余搜索，在多个问答基准测试中展示了改进的性能和效率。 AI

影响该框架可能带来更高效、更强大的AI搜索代理，降低计算成本并提高信息检索任务的性能。

排序理由该集群包含一篇详细介绍新AI代理训练框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新AI代理训练框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Sheng-Jun Huang · 2026-10-29 09:28

面向零标签工具高效搜索代理的异构协同进化学习

Deep search agents extend language models by interleaving reasoning with external retrieval. However, effective search-agent training requires addressing two challenges beyond final-answer optimization. First, the capability frontier of agents is largely determined by training qu…

本文如何被排名

报道来源 [1]

面向零标签工具高效搜索代理的异构协同进化学习

相关实体

相关话题