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

Source: [SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking](<https://www.sota2.com/research/paper/68fa78c01e209131cea7a477>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:16.911Z

Authors: Junnan Liu, Linhao Luo, Thuy-Trang Vu, Gholamreza Haffari

Published: 2025-05-25T20:20:04.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.19300>)

[PDF](<https://arxiv.org/pdf/2505.19300.pdf>)
