Agents

WANDR tests how well agents discover large sets of entities and verify specific facts about each one. It provides a dense, interpretable eva…

WANDR tests how well agents discover large sets of entities and verify specific facts about each one. It provides a dense, interpretable eval signal that reveals whether an agent fails, and where. The

DGX agentx-post
agentsperplexity--x

WANDR tests how well agents discover large sets of entities and verify specific facts about each one. It provides a dense, interpretable eval signal that reveals whether an agent fails, and where. The pipeline also doubles as a semi-automated factory for training data.

Related

Source: Perplexity (X) | 2026-07-14

Loading related sources…