English(EN) Perplexity has released WANDR, an open benchmark with 500 evidence-heavy tasks for testing research agents. The benchmark evaluates whether agents can discover

Perplexity 推出 WANDR 基准测试 AI 研究代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-19 11:53

Perplexity 推出了 WANDR，一个旨在评估研究代理的新开放基准。该基准包含 500 个任务，要求代理查找和引用证据来支持其发现。在初步测试中，Perplexity Search as Code 以 0.363 的软 F1 分数获得最高分。 AI

影响该基准可以加速能够进行复杂信息检索和基于证据推理的 AI 代理的开发和评估。

排序理由该集群描述了一个用于评估 AI 研究代理的新基准的发布。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — fosstodon.org 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一个用于评估 AI 研究代理的新基准的发布。[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: product, other; 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: 81 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-07-19 11:53

Perplexity 发布 WANDR，一个包含 500 个证据密集型任务的开放基准，用于测试研究代理。该基准评估代理是否能够发现

Perplexity has released WANDR, an open benchmark with 500 evidence-heavy tasks for testing research agents. The benchmark evaluates whether agents can discover many qualifying entities and back each with cited evidence. Perplexity Search as Code leads at 0.363 soft F1. https://ww…

本文如何被排名

报道来源 [1]

Perplexity 发布 WANDR，一个包含 500 个证据密集型任务的开放基准，用于测试研究代理。该基准评估代理是否能够发现

相关实体

相关话题