VEvo-Harness is a causally-guarded, continual self‑evolving system designed to improve agentic image generation. It introduces a visual traceback mechanism, visual continual governance, a lifecycle‑managed harness state, and a heterogeneous sandbox policy to ensure only causally valid skill updates are incorporated. The system outperforms existing agentic methods and rivals proprietary generators while preserving continual evolution and generalization.
arXiv:2607. 01709v1 Announce Type: new Abstract: Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently.
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.
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.
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. 13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps.
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:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language m...
arXiv:2607. 12042v1 Announce Type: cross Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation.
VETR (Verified Execution Trajectories for Refinement) is a framework that enables visual agents to recursively improve symbolic graphics reasoning by extracting actionable evidence from execution traces. It retains aligned program/render records and uses an execution refiner to compile observed writes and state changes into constrained alternative programs, which are then validated against captured runtime state. Evaluations on BlenderGym and BlenderBench with GPT‑5.6‑luna and Qwen3.8‑27B demonstrate that VETR consistently outperforms existing refinement strategies such as BlenderAlchemy and VIGA.
arXiv:2607. 26598v1 Announce Type: cross Abstract: Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions.
arXiv:2608. 05446v1 Announce Type: new Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.
arXiv:2610.19424v1 Announce Type: new Abstract: LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reaso...