V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning

Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a persistent challenge. Although recent agentic approaches incorporate tool use, they often neglect critical execution feedback. Consequently, they suffer from the imagination-actionobserver (IAO) bias, a misalignment between prior imagination and observer feedback that undermines reasoning stability and optimality. To bridge this gap, we introduce V-ABS, an actionobserver driven beam search framework that enables deliberate reasoning through thinker-actorobserver iterations. We also propose an entropybased adaptive weighting algorithm to mitigate the IAO bias by dynamically balancing the confidence scores between the policy priors and the observational feedback. Moreover, we construct a large-scale supervised fine-tuning (SFT) dataset comprising over 80k samples to guide the model to assign higher prior confidence to correct action paths. Extensive experiments across eight diverse benchmarks show that V-ABS achieves state-of-the-art performance, delivering an average improvement of 19.7% on the Qwen3-VL-8B baseline and consistent gains across both opensource and proprietary models. Code is available at https://github.com/pami-zwning/ V-ABS .