OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
What this work does
OpenVLHarness combines consistent tool interfaces, interpretable evidence rendering, and a per-query multimodal artifact registry. Agents can revisit images, masks, arrays, and web references and compute over earlier results during iterative investigations.
THE RESEARCH CONVERSATION
Discussion & reactions
Share a question, an insight, or a replication experience. Sign in with GitHub to join the conversation.