@PKUCXK: You can try the following two prompts in the Thinking mode (via web/app) to get a better model experience in certain do…
Summary
Xiaokang Chen shares two prompts, 'Think with Grounding' and 'Think with Pointing', to improve model performance in domains like counting in Thinking mode. These prompts use bounding boxes and points to make the MLLM's reasoning more human-like.
View Cached Full Text
Cached at: 06/20/26, 08:24 PM
You can try the following two prompts in the Thinking mode (via web/app) to get a better model experience in certain domains like counting (Note: keep a line break after the bracketed titles)::
[Think with Grounding] …….
[Think with Pointing] ……
These two prompts encourage the model to adopt bounding boxes or points (which are classic fundamentals in computer vision) in its thought process.
Personally, I love the pointing approach for solving abstract topological/reasoning tasks. Using points to represent continuous trajectories makes the MLLM’s reasoning process feel much more human-like.
Speaking purely from my personal exploration: Getting a multimodal model to accurately represent continuous trajectories with points is still a highly challenging frontier task for the entire industry. The current performance on real-world scenarios still has a long way to go.
Xiaokang Chen (@PKUCXK): Vision is now live on web and app. 👀
Come test the new eyes, but give its pure text capabilities a try while you’re at it.
Similar Articles
When Prompts Become Pixels: Prompt-Region Grounding for Multimodal Reasoning
This paper introduces Visualized Task Semantics (VTS), a controlled intervention to study when multimodal LLMs are asked questions in the image rather than text. It reveals a consistent accuracy drop across all tested models and tasks, and proposes prompt-region grounding to recover the clean task representation, improving VTS accuracy from 58.0 to 66.3.
Thinking with Visual Grounding
This paper introduces visually grounded thinking, a method for vision-language models to interleave natural-language reasoning with explicit visual evidence grounding using points or boxes. A scalable synthesis pipeline and grounding-aware reinforcement learning improve reasoning accuracy, enabling a 4B model to match or surpass a 27B model on spatial and counting benchmarks.
Try out this "high" reasoning mode for 27B (tested on VLLM)
The author experimented with the 27B model on VLLM and created a 'high' reasoning mode by blending prompts from low and xhigh modes, resulting in more efficient and enjoyable reasoning output.
@wlzh: Microsoft + UPenn Open-Source Multiplex Thinking: Let LLMs 'Clone' at Forks Then Merge. In a nutshell: When reasoning reaches a critical decision point, the model 'clones' into K pathfinders, each taking a different path. After one step, they merge back into a composite token and continue. With K=3, one token carries the information of three…
Microsoft and the University of Pennsylvania open-source Multiplex Thinking, which allows LLMs to split into K parallel paths during inference, explore, then merge, improving efficiency. On a 7B model, it achieves over 50% accuracy on AMC2023 (first 7B model to do so) and over 55% on AIME2025.
MAI-Thinking-1
Microsoft AI introduces MAI-Thinking-1, a 35B-active parameter reasoning model trained from scratch without distillation, achieving strong performance on software engineering and math benchmarks while emphasizing clean data and self-sufficiency.