MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

• URL: http://arxiv.org/abs/2512.23412v2
• Date: Wed, 07 Jan 2026 10:27:34 GMT
• Title: MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
• Authors: Jiawei Chen, Xintian Shen, Lihao Zheng, Zhenwei Shao, Handong Cui, Chaoqun Du, Li Gong, Feng Gu, Xuefeng Hao, Wei He, Jiabang He, Yi Hu, Bin Huang, Shanshan Li, Qizhen Li, Jing Luo, Zide Liu, Xiaobo Liu, Ning Mao, Lifu Mu, Xuhao Pan, Zhiheng Qu, Chang Ren, Xudong Rao, Haoyi Sun, Qian Wang, Shuai Wang, Zhichao Wang, Wei Wang, Lian Wen, Jiqing Zhan, Hongfu Yang, Sheng Yang, Jiajun Yang, Pengfei Yu, Hongyuan Zhang, Bin Zhang, Chunpeng Zhou, Zheng Zhou, Shucheng Zhou, Shuo Xie, Yun Zhu, Hao Ma, Tao Wei, Pan Zhou, Wei Chen,
• Abstract summary: We introduce MindWatcher, a tool-integrated reasoning agent with interleaved thinking and multimodal chain-of-thought (CoT) reasoning.<n>MindWatcher can autonomously decide whether and how to invoke diverse tools and coordinate their use.<n>A large-scale, high-quality local image retrieval database, covering eight categories including cars, animals, and plants, endows model with robust object recognition.
• Score: 55.221850286246
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of autonomous reasoning and tool invocation are rapidly emerging as a powerful approach for complex decision-making tasks involving multi-step interactions with external environments. In this work, we introduce MindWatcher, a TIR agent integrating interleaved thinking and multimodal chain-of-thought (CoT) reasoning. MindWatcher can autonomously decide whether and how to invoke diverse tools and coordinate their use, without relying on human prompts or workflows. The interleaved thinking paradigm enables the model to switch between thinking and tool calling at any intermediate stage, while its multimodal CoT capability allows manipulation of images during reasoning to yield more precise search results. We implement automated data auditing and evaluation pipelines, complemented by manually curated high-quality datasets for training, and we construct a benchmark, called MindWatcher-Evaluate Bench (MWE-Bench), to evaluate its performance. MindWatcher is equipped with a comprehensive suite of auxiliary reasoning tools, enabling it to address broad-domain multimodal problems. A large-scale, high-quality local image retrieval database, covering eight categories including cars, animals, and plants, endows model with robust object recognition despite its small size. Finally, we design a more efficient training infrastructure for MindWatcher, enhancing training speed and hardware utilization. Experiments not only demonstrate that MindWatcher matches or exceeds the performance of larger or more recent models through superior tool invocation, but also uncover critical insights for agent training, such as the genetic inheritance phenomenon in agentic RL.

Related papers

• 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)
• DeepEyesV2: Toward Agentic Multimodal Model [3.775371242454792]
  Agentic multimodal models should not only comprehend text and images, but also actively invoke external tools, such as code execution environments and web search, and integrate these operations into reasoning.<n>We introduce DeepEyesV2, and explore how to build an agentic multimodal model from the perspectives of data construction, training methods, and model evaluation.<n>We evaluate DeepEyesV2 on RealX-Bench and other representative benchmarks, demonstrating its effectiveness across real-world understanding, mathematical reasoning, and search-intensive tasks.
  arXiv  Detail & Related papers  (2025-11-07T14:31:20Z)
• DeepAgent: A General Reasoning Agent with Scalable Toolsets [111.6384541877723]
  DeepAgent is an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution.<n>To address the challenges of long-horizon interactions, we introduce an autonomous memory folding mechanism that compresses past interactions into structured episodic, working, and tool memories.<n>We develop an end-to-end reinforcement learning strategy, namely ToolPO, that leverages LLM-simulated APIs and applies tool-call advantage attribution to assign fine-grained credit to the tool invocation tokens.
  arXiv  Detail & Related papers  (2025-10-24T16:24:01Z)
• AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning [17.086082843274003]
  Large Language Models (LLMs) evolve into powerful Large Reasoning Models (LRMs)<n>Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools.<n>Inspired by the human ability to adaptively select tools, we introduce AutoTIR, a reinforcement learning framework.
  arXiv  Detail & Related papers  (2025-07-29T14:12:28Z)
• Acting Less is Reasoning More! Teaching Model to Act Efficiently [87.28134636548705]
  Tool-integrated reasoning augments large language models with the ability to invoke external tools to solve tasks.<n>Current approaches typically optimize only for final correctness without considering the efficiency or necessity of external tool use.<n>We propose a framework that encourages models to produce accurate answers with minimal tool calls.<n>Our approach reduces tool calls by up to 68.3% and improves tool productivity by up to 215.4%, while maintaining comparable answer accuracy.
  arXiv  Detail & Related papers  (2025-04-21T05:40:05Z)
• 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)
• ART: Automatic multi-step reasoning and tool-use for large language models [105.57550426609396]
  Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings. Each reasoning step can rely on external tools to support computation beyond the core LLM capabilities. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate reasoning steps as a program.
  arXiv  Detail & Related papers  (2023-03-16T01:04:45Z)

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.