Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration

• URL: http://arxiv.org/abs/2602.11241v1
• Date: Wed, 11 Feb 2026 17:29:17 GMT
• Title: Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
• Authors: Jinghan He, Junfeng Fang, Feng Xiong, Zijun Yao, Fei Shen, Haiyun Guo, Jinqiao Wang, Tat-Seng Chua,
• Abstract summary: We propose a framework that shifts from passive interaction to active exploration of visual environments.<n>Active-Zero employs three co-evolving agents: a Searcher that retrieves images from open-world repositories based on the model's capability frontier.<n>On Qwen2.5-VL-7B-Instruct across 12 benchmarks, Active-Zero 53.97 average accuracy on reasoning tasks (5.7% improvement) and 59.77 on general understanding (3.9% improvement)
• Score: 72.84714132070404
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collections, resulting in strong dependence on initial datasets and inefficient learning. Without the ability to actively seek visual data tailored to their evolving capabilities, agents waste computational effort on samples that are either trivial or beyond their current skill level. To address these limitations, we propose Active-Zero, a framework that shifts from passive interaction to active exploration of visual environments. Active-Zero employs three co-evolving agents: a Searcher that retrieves images from open-world repositories based on the model's capability frontier, a Questioner that synthesizes calibrated reasoning tasks, and a Solver refined through accuracy rewards. This closed loop enables self-scaffolding auto-curricula where the model autonomously constructs its learning trajectory. On Qwen2.5-VL-7B-Instruct across 12 benchmarks, Active-Zero achieves 53.97 average accuracy on reasoning tasks (5.7% improvement) and 59.77 on general understanding (3.9% improvement), consistently outperforming existing self-play baselines. These results highlight active exploration as a key ingredient for scalable and adaptive self-evolving vision-language systems.

Related papers

• Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes [54.50887214639301]
  We propose an innovative approach that harnesses web-crawled descriptions, leveraging a large-language model to extract relevant keywords.<n>This method reduces the need for human annotators and eliminates the laborious manual process of attribute data creation.<n>In our zero-shot experiments, our model achieves accuracies of 81.0%, 53.1%, and 68.9% on UCF-101, HMDB-51, and Kinetics-600, respectively.
  arXiv  Detail & Related papers  (2025-10-31T07:45:44Z)
• Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models [63.69856480318313]
  AGILE formulates jigsaw solving as an interactive process, enabling the model to progressively engage with the environment.<n>We show that AGILE substantially boosts performance on jigsaw tasks of varying complexity.<n>We also demonstrate strong generalization across 9 general vision tasks, achieving an average improvement of 3.1%.
  arXiv  Detail & Related papers  (2025-10-01T17:58:05Z)
• Stochastic Encodings for Active Feature Acquisition [100.47043816019888]
  Active Feature Acquisition is an instance-wise, sequential decision making problem.<n>The aim is to dynamically select which feature to measure based on current observations, independently for each test instance.<n>Common approaches either use Reinforcement Learning, which experiences training difficulties, or greedily maximize the conditional mutual information of the label and unobserved features, which makes myopic.<n>We introduce a latent variable model, trained in a supervised manner. Acquisitions are made by reasoning about the features across many possible unobserved realizations in a latent space.
  arXiv  Detail & Related papers  (2025-08-03T23:48:46Z)
• From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation [35.79160868966466]
  We propose FSD (From Seeing to Doing), a novel vision-language model that generates intermediate representations through spatial relationship reasoning.<n>Our approach combines a hierarchical data pipeline for training with a self-consistency mechanism that aligns spatial coordinates with visual signals.<n>We show that FSD achieves 40.6% success rate in SimplerEnv and 72% success rate across 8 real-world tasks, outperforming the strongest baseline by 30%.
  arXiv  Detail & Related papers  (2025-05-13T13:20:46Z)
• Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge [62.981429762309226]
  The ability to actively ground task instructions from an egocentric view is crucial for AI agents to accomplish tasks or assist humans virtually. We propose to improve phrase grounding models' ability on localizing the active objects by: learning the role of objects undergoing change and extracting them accurately from the instructions. We evaluate our framework on Ego4D and Epic-Kitchens datasets.
  arXiv  Detail & Related papers  (2023-10-23T16:14:05Z)
• Tool-Augmented Reward Modeling [58.381678612409]
  We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments. Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources. In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
  arXiv  Detail & Related papers  (2023-10-02T09:47:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.