LongBanana is the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis, featuring 90 tasks each with about 32 reference images, 20 constraints, and 50 evaluation items, totaling 4,670 atomic evaluation items. The benchmark uses a graph-grounded evaluation design that converts entity-relation graph obligations into checklist items for Content Fidelity, Relational Binding, and Global Constraint Satisfaction. An accompanying agent-harness framework, LongBanana-Gen, demonstrates that minimal harnesses improve generation quality, with a ReAct-Plan-Exec-Reflect workflow further enhancing evidence grounding and repair.
arXiv:2610.32459v1 Announce Type: new Abstract: Image generation models have rapidly advanced, with many models now supporting generation conditioned on multiple reference images and textual instruct...
WeAgent-MMGenEdit is a comprehensive framework for multimodal agentic image generation and editing that addresses the unreliability of current models when prompts require external world knowledge. It introduces a multimodal harness with persistent evidence management, a scalable data construction pipeline producing 23K supervised trajectories and 14.7K RL tasks, and a bilingual benchmark (WeBench-MMGenEdit) for knowledge-intensive generation and multi-image editing. Post‑training methods based on SFT and RL further refine the agent policy and image backend, enabling a 30B‑parameter policy to outperform similarly sized models and approach the performance of a 1T‑parameter agent.
The paper introduces WeGenEditBench, a benchmark with 2,740 evaluation instances and 148 task types for image editing, focusing on local failure detection and prioritization for model improvement. It also presents WeGenEvoStudio, a multi‑agent harness that supports recursive self‑improvement by diagnosing failures, constructing retrieval‑grounded data, and adapting models. Experiments show that models such as GPT‑Image‑2 and Seedream‑5.0‑Pro excel in single‑image and text‑intensive editing, and evolution experiments demonstrate significant targeted gains on selected benchmarks.
ATP‑Bench proposes a new benchmark for evaluating agentic tool planning in multimodal large language models (MLLMs) that generate interleaved text-and-image responses. The benchmark contains 7,702 QA pairs, including 1,592 visual‑question‑answer pairs, across eight categories and 25 visual‑critical intents, all verified by humans. A Multi‑Agent MLLM‑as‑a‑Judge (MAM) system is introduced to assess tool‑call precision, missed opportunities, and overall response quality without relying on ground‑truth references.
OneSearch‑VL is a unified multimodal deep research agent that handles single‑image, multi‑image, and video tasks by leveraging a Visually Grounded Evidence Graph (VGEG) to encode dependencies among visual anchors, entity relations, facts, and answer‑producing operations. The VGEG‑based data engine builds and verifies questions, filters expert trajectories, and supports supervised fine‑tuning (SFT) and reinforcement learning (RL) with the Evidence‑aware Visual‑Grounded Rubric reward (EVGR). Experiments demonstrate that OneSearch‑VL‑8B outperforms Qwen3‑VL‑8B with tool access by 20.2 and 17.6 percentage points on new multimodal benchmarks, while also achieving significant gains across seven image benchmarks and VideoDR.
Recent advances in multimodal generative models have enabled instruction-based image generation to move beyond semantic manipulation to knowledge-driven visual reasoning. However, these methods focus on explicit commonsense reasoning, shallow causal understanding, and direct knowledge recall, failing at knowledge-intensive generation.
The paper introduces a visual-native agent harness that registers every tool‑returned image as an addressable reference, enabling reuse of intermediate visual evidence in multimodal deep search tasks. It also proposes On‑Policy Data Evolution (ODE), a closed‑loop data generator that refines training data across rounds based on policy rollouts, targeting the agent’s evolving needs. Experiments on eight benchmarks show ODE boosts the Qwen3‑VL‑8B agent’s performance from 24.9% to 39.0% on average, and from 30.6% to 41.5% at 30B, while validating the benefits of image bank reuse and rollout‑feedback evolution.
arXiv:2607. 05465v1 Announce Type: cross Abstract: Complex image creation and editing often require more than a single generation or editing model.
Stride is a multi‑agent framework for infographic generation that separates constraint evaluation from visual grounding, routing global revisions to a composer subagent and local corrections to a retoucher subagent. Each subagent plans internally and produces multiple candidates, and Stride accepts only those that improve a verifier score, thereby preventing regression across iterations. This scale‑aware, redundancy‑rich approach yields stable improvement and outperforms proprietary systems on several benchmarks, achieving state‑of‑the‑art results on WISE and strong performance on BizGenEval and IGenBench.
arXiv:2608. 16765v1 Announce Type: cross Abstract: Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain organized around predefined task types (e.
The paper introduces EvidenceConnect, a data‑synthesis framework that generates training examples by zooming into related image regions to create questions requiring comparison, aggregation, or chaining of visual evidence. By retaining only reference answers agreed upon by independent vision‑language models and discarding questions that survive region ablation, the authors train base VLMs with RLVR to produce Zooming without Zooming v2 (ZwZ2). Although the synthesized data are not benchmark‑specific, ZwZ2 shows improvements across fine‑grained and spatial perception, embodied spatial reasoning, multimodal long‑context understanding, multimodal agent tasks, and general visual reasoning, demonstrating that strengthening the shared capability of connecting evidence yields more generalizable multimodal perception.
The paper introduces Mosaic, a multi-image visual harness that lets large language‑vision models (MLLMs) construct visual intermediates using ten composable image operations. It evaluates five re‑representation settings on existing multi‑image benchmarks and a new grounding‑focused benchmark, MosaicBench, finding that visual re‑representation benefits tasks requiring precise visual evidence more than those dominated by high‑level semantics. MosaicAgent‑8B is trained via reinforcement learning to compose these operations without demonstration trajectories, demonstrating diverse problem‑solving patterns.