Beacon: Knowing When and How to Perform Agentic Visual Reasoning

• URL: http://arxiv.org/abs/2607.28595v1
• Date: Thu, 30 Jul 2026 17:46:55 GMT
• Title: Beacon: Knowing When and How to Perform Agentic Visual Reasoning
• Abstract summary: We propose a novel agentic visual reasoning model that achieves stronger overall performance, improved Mode Adaptiveness, and genuine tool-induced performance gains.<n>At the core of Beacon are the Necessity-Aware Adaptive Reward and the Hint-Guided Capability Expansion mechanism in the reinforcement learning stage.
• Score: 35.34377563874046
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The fundamental goal of agentic visual reasoning is to improve the success rate of multimodal large language models (MLLMs) on complex tasks, rather than merely equipping them with a sophisticated yet inefficient reasoning paradigm. In this work, we rethink agentic visual reasoning through two key dimensions of tool use: Mode Adaptiveness (MA) and Tool Effect (TE). Mode Adaptiveness characterizes whether an MLLM can recognize when tools are truly necessary and invoke them accordingly, thereby avoiding unnecessary computational overhead while improving performance on challenging problems that require tool assistance. Tool Effect characterizes the actual impact of tool use: tools should extend the model's capabilities on problems unsolvable through text-only reasoning, while avoiding additional errors on problems that the model can already solve without tools. We conduct a comprehensive analysis to quantify these two properties and empirically reveal that existing agentic visual reasoning models exhibit limited Mode Adaptiveness, while the gains produced by tool use on hard examples are largely offset by the harm introduced on easy examples that the models can already solve. Motivated by these observations, we propose Beacon, a novel agentic visual reasoning model that achieves stronger overall performance, improved Mode Adaptiveness, and genuine tool-induced performance gains. At the core of Beacon are the Necessity-Aware Adaptive Reward and the Hint-Guided Capability Expansion mechanism in the reinforcement learning stage, which respectively encourage adaptive tool invocation based on task necessity and strengthen the model's tool-use capability on the most challenging problems. Extensive experiments across diverse benchmarks demonstrate the strong overall performance of Beacon and its substantial improvements in both Mode Adaptiveness and Tool Effect.

Related papers

• Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools [65.7098588070281]
  We propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability.<n>BEE incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism.<n>BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks.
  arXiv  Detail & Related papers  (2026-07-13T05:32:00Z)
• Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning [44.46498720264651]
  We introduce AutoTool, a model that adaptively decides whether to invoke tools according to the characteristics of each query.<n>Within a reinforcement learning framework, we design an explicit dual-mode reasoning strategy with mode-specific reward functions.<n>Experiments demonstrate that AutoTool exhibits outstanding performance and high efficiency.
  arXiv  Detail & Related papers  (2026-05-19T13:44:26Z)
• What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom [26.940122024948597]
  We introduce MED (Measure-Explain-Diagnose) to disentangle intrinsic capability changes from tool-induced effects.<n>We find that improvements are dominated by intrinsic learning, while tool-use RL mainly reduces tool-induced harm.<n>Overall, current vision tool-use RL learns to coexist safely with tools rather than master them.
  arXiv  Detail & Related papers  (2026-02-01T17:00:50Z)
• AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning [66.24374176797075]
  We introduce textbfAdaReasoner, a family of multimodal models that learn tool use as a general reasoning skill rather than as tool-specific or explicitly supervised behavior.<n>AdaReasoner is enabled by (i) a scalable data curation pipeline exposing models to long-horizon, multi-step tool interactions; (ii) Tool-GRPO, a reinforcement learning algorithm that prioritizes tool selection and sequencing based on end-task success; and (iii) an adaptive learning mechanism that dynamically regulates tool usage.
  arXiv  Detail & Related papers  (2026-01-26T16:04:43Z)
• 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)
• Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates [56.73907811047611]
  Large language models (LLMs) have demonstrated strong reasoning and tool-use capabilities.<n>LLMs often fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.<n>We introduce a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function callings.
  arXiv  Detail & Related papers  (2025-09-22T17:55:14Z)
• ToolACE-DEV: Self-Improving Tool Learning via Decomposition and EVolution [77.86222359025011]
  We propose ToolACE-DEV, a self-improving framework for tool learning.<n>First, we decompose the tool-learning objective into sub-tasks that enhance basic tool-making and tool-using abilities.<n>We then introduce a self-evolving paradigm that allows lightweight models to self-improve, reducing reliance on advanced LLMs.
  arXiv  Detail & Related papers  (2025-05-12T12:48:30Z)
• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use.<n>MeCo quantifies metacognitive scores by capturing high-level cognitive signals in the representation space.<n>MeCo is fine-tuning-free and incurs minimal cost.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)

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.