EvoGen-Harness is a generator‑agnostic framework that enables multi‑responsibility evolution of image‑generation harnesses, allowing multiple external components to adapt around frozen generators. It introduces Trace, a method that aggregates evidence across stochastic runs, uses failure attribution as a search prior, and progressively re‑attributes residual failures to guide efficient evolution. The approach achieves significant performance gains on GenEval2, T2I‑CompBench++, and WISE, with high attribution recall, No‑Patch accuracy, and low regression rates.
Modern text-to-image (T2I) systems can be improved without modifying generator parameters by adapting the external system around frozen generators. However, existing approaches typically optimize a pr...
arXiv:2610.13502v1 Announce Type: new Abstract: Infographic generation challenges text-to-image models because a single image must satisfy numerous visual, textual, and semantic constraints. Iterativ...
arXiv:2610.10426v1 Announce Type: new Abstract: Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Exist...
arXiv:2610.12899v1 Announce Type: new Abstract: Few-step text-to-image generators produce high-quality images with few network forward passes, yet struggle with complex prompts involving multiple sub...
arXiv:2609.14857v1 Announce Type: new Abstract: Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve executio...
arXiv:2606. 01803v1 Announce Type: new Abstract: The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling.
arXiv:2609.40048v1 Announce Type: new Abstract: Ultra-long video temporal grounding requires balancing long-range evidence search with fine-grained event understanding under a limited visual budget,...
HarnessEvolve is a self‑evolving framework that improves agent harnesses—prompts, skills, tools, and execution logic—by learning from reference trajectories. It separates execution, evaluation, optimization, and gating into independent modules, addressing credit assignment failure, shortcut learning, and catastrophic forgetting. The approach uses reference trajectories to extract error signals, applies quality and performance gates to candidate updates, and validates updates on held‑out data, consistently outperforming state‑of‑the‑art baselines across diverse benchmarks.
VICO proposes a co‑evolutionary framework where a vision‑language model (actor) and an Environment‑as‑Rewriter (EnvRewriter) are trained together. The EnvRewriter edits visual structures—such as scene graphs, chart tables, or protected region masks—to generate new training samples whose difficulty is calibrated to the actor’s current performance via a pass‑rate reward. Across nine multimodal benchmarks, VICO‑8B outperforms its base model by up to +5.0 % on out‑of‑domain tasks and surpasses other co‑evolution baselines while requiring far fewer labeled samples.
Terminal-agent capability depends jointly on model weights and the runtime harness that formats prompts, binds tools, and handles error recovery. Existing harness-model co-evolution approaches improve...
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.
arXiv:2607. 13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps.