The paper investigates how fine‑grained credit assignment affects learning in multimodal agentic reinforcement learning, using video editing as a testbed. Four movie‑trailer editing tasks—Content Selection, Narrative Sequencing, Rough Cut, and Fine Cut—are introduced to represent real‑world editing workflows with varying complexity and horizon lengths. The study finds that decaying process rewards significantly boost performance on the long‑horizon Fine Cut task, while offering modest gains on shorter tasks; however, fixed process‑reward weighting can lead to reward‑hacking and degraded outcomes, and on‑policy self‑distillation provides limited benefit.
arXiv:2608. 02694v1 Announce Type: cross Abstract: Long-horizon video editing agents receive final-product feedback only after many interdependent decisions.
arXiv:2605.20342v3 Announce Type: replace Abstract: Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a pro...
Recent breakthroughs in instruction-based image editing have captured significant attention, as models are now capable of handling real-world editing demands with the practicality required by everyday users. However, editing models trained primarily for single-turn edits often break down in multi-turn editing--the natural interactive setting where a user iteratively refines an image based on the model's own previous outputs.
arXiv:2610.15840v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language model (LLM) agents remains challenging in long-horizon tasks with sparse outcome rewards, where assign...
arXiv:2606. 27608v1 Announce Type: cross Abstract: We present Qwen-Image-2.
arXiv:2609.37250v1 Announce Type: cross Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrai...
arXiv:2610.16224v1 Announce Type: cross Abstract: Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challen...
The paper introduces RC‑GRPO‑Editing, a region‑constrained Group Relative Policy Optimization framework for flow‑based image editing. It localizes exploration by decoupling initial noise perturbations to reduce background‑induced reward variance and adds an attention concentration reward to keep cross‑attention focused on the intended editing region. Experiments on CompBench demonstrate consistent gains in instruction adherence within the editing region while better preserving non‑target content.
arXiv:2609.05588v3 Announce Type: replace-cross Abstract: World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video and action-labeled inte...
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
arXiv:2602. 19313v2 Announce Type: replace-cross Abstract: General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior.
arXiv:2605. 06094v5 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories.