AIarXiv
Ranked by formulaVerdict: NotableOpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks…
Key numbers
- 37% of their model-token cost
Caveats
- Preprint; not yet peer reviewed.
VerdictWorth a reader's time today.
Abstract
Multimodal large language models (MLLMs) have made rapid progress on visual reasoning, yet many tasks require evidence that is difficult to obtain through internal reasoning alone: our controlled study on 22 benchmarks shows that simply increasing the inference budget of the base model yields only modest gains. Such tasks demand grounded perception, external knowledge, and numerical measurements obtained through heterogeneous tools, whose outputs must be made interpretable to the model and retained across reasoning steps. We introduce OpenVLHarness, a multimodal reasoning harness organized around a capability layer and persistent multimodal memory. The capability layer combines task-level tool interfaces with evidence rendering, providing consistent access to heterogeneous backends and converting their outputs into model-readable observations. Persistent multimodal memory retains the corresponding images, structured data, and web references as addressable artifacts throughout each query. A coding interface executes generated programs over stored data, enabling computations that combine results from multiple tools. Together, these mechanisms support an iterative process of acquiring, inspecting, and composing multimodal evidence. Evaluated on 22 benchmarks with eight open and proprietary backbones, OpenVLHarness improves average scores by 9.7-12.6 points over matched no-tool baselines, including +11.2 with Qwen3-VL-8B, +9.7 with Kimi K3, and +9.9 with GPT-6 Astra. With GPT-6 Luna at medium reasoning effort, OpenVLHarness outperforms the base model, Codex, and Visual Sketchpad at maximum effort by 7.7-8.5 points while incurring at most 37% of their model-token cost.
The editor's rubric
- Leverage4 / 5
- A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).
- Magnitude3 / 5
- Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
- Evidence3 / 5
- Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
- Novelty2 / 5
- A new combination of known ideas.
- Trajectory2 / 5
- Some room to improve with obvious engineering.
- Stakes2 / 5
- Benefits a professional community (practitioners, clinicians, engineers).
Editor’s rationale
Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); breadth (many tasks); gains (outperforms); verification (multiple benchmarks); stakes (general AI).
How the score was computed
Desks place stronger verdicts first, then use this score to order work within the same verdict.
- Merit
- 5.6 / 10
- Adjusted merit
- 4.6 / 10
- Attention
- 85%
- Freshness
- 80%
- Hugging Face upvotes69 (reference 25, via hf-daily, Oct 20, 2026, 13:49 UTC)
- GitHub stars18 (reference 250, via hf-daily, Oct 20, 2026, 13:49 UTC)