# SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking

arXiv: https://arxiv.org/abs/2505.19300 · HTML: https://mlsanity.com/paper/2505.19300/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 0 of its 56 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Built on by (most cited first, 2 of 2)

- [Rectifying LLM Thought from Lens of Optimization](https://mlsanity.com/paper/2512.01925/) (2025)
- [AIPO: Learning to Reason from Active Interaction](https://mlsanity.com/paper/2605.08401/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) demonstrate their impressive reasoning capabilities. However, the reasoning confined to internal parametric space limits LLMs' access to real-time information and understanding of the physical world. To overcome this constraint, we introduce SituatedThinker, a novel framework that enables LLMs to ground their reasoning in real-world contexts through situated thinking, which adaptively combines both internal knowledge and external information with predefined interfaces. By utilizing reinforcement learning, SituatedThinker incentivizes deliberate reasoning with the real world to acquire information and feedback, allowing LLMs to surpass their knowledge boundaries and enhance reasoning. Experimental results demonstrate significant performance improvements on multi-hop question-answering and mathematical reasoning benchmarks. Furthermore, SituatedThinker demonstrates strong performance on unseen tasks, such as KBQA, TableQA, and text-based games, showcasing the generalizable real-world grounded reasoning capability. Our codes are available at https://github.com/jnanliu/SituatedThinker.