# MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning arXiv: https://arxiv.org/abs/2512.23412 ยท HTML: https://mlsanity.com/paper/2512.23412/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. - Builds on 36 of its 42 references that are in the map. - First posted on arXiv 29 Dec 2025. ## Placed in - LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/) ## Builds on (most cited first, 30 of 36) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022) - [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023) - [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023) - [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025) - [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024) - [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025) - [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024) - [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023) - [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023) - [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025) - [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022) - [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025) - [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025) - [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025) - [WebWalker: Benchmarking LLMs in Web Traversal](https://mlsanity.com/paper/2501.07572/) (2025) - [Agentic Reinforced Policy Optimization](https://mlsanity.com/paper/2507.19849/) (2025) - [WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent](https://mlsanity.com/paper/2508.05748/) (2025) - [MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines](https://mlsanity.com/paper/2409.12959/) (2024) - [WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents](https://mlsanity.com/paper/2509.13309/) (2025) - [SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models](https://mlsanity.com/paper/2502.13059/) (2025) - [Detecting and Evaluating Medical Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2406.10185/) (2024) - [SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis](https://mlsanity.com/paper/2505.16834/) (2025) - [rStar2-Agent: Agentic Reasoning Technical Report](https://mlsanity.com/paper/2508.20722/) (2025) - [WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research](https://mlsanity.com/paper/2509.13312/) (2025) - [Scaling Agents via Continual Pre-training](https://mlsanity.com/paper/2509.13310/) (2025) ## Built on by (most cited first, 6 of 6) - [AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios](https://mlsanity.com/paper/2602.23166/) (2026) - [Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning](https://mlsanity.com/paper/2602.01983/) (2026) - [Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?](https://mlsanity.com/paper/2604.03016/) (2026) - [StreamingClaw Technical Report](https://mlsanity.com/paper/2603.22120/) (2026) - [Evaluating the Search Agent in a Parallel World](https://mlsanity.com/paper/2603.04751/) (2026) - [MM-ContextFold: Context Folding for Multimodal Agentic Retrieval](https://mlsanity.com/paper/2609.23121/) (2026) ## Abstract (arXiv) 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.