Taramandal-GPT improves solving astrodynamics problems with knowledge retrieval
Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking
Computation and LanguageArtificial Intelligence
Summary
Large language models usually struggle with complex space science problems because they require detailed steps and special terms. The authors created Taramandal-GPT, which uses a smart retrieval system to look up important information and a step-by-step thinking approach to improve answers. It was tested on a set of 299 space science questions and showed good performance, especially on problems that need careful reasoning. This work shows how specialized AI tools can better help with space exploration and engineering tasks.
What this means in practice
- •For spacecraft engineers: Use Taramandal-GPT to assist in solving complex spacecraft design and navigation problems requiring accurate multi-step reasoning.
- •For satellite operations teams: Integrate the system to improve decision support in orbital mechanics challenges using domain-relevant knowledge retrieval.
Authors
Akhil Sharma, Jatin Gupta, Ali Imam Abidi
Abstract
Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astronomy and astrodynamics remains limited due to challenges in multi-step reasoning, symbolic manipulation, and domain-specific terminology. To address this, we present Taramandal-GPT (Constellation-GPT), a domain-adapted framework built on the Qwen3-8b backbone, enhanced with a Retrieval-Augmented Generation (RAG) pipeline and a fallback mechanism for improved contextual precision. We evaluate it on the Astrodynamics Problems Benchmark (APBench), a dataset of 299 questions covering foundational to advanced levels of space science. Using a dual evaluation method - numeric margin-based scoring and semantic similarity assessment - Taramandal-GPT achieves competitive performance against state-of-the-art open- and closed-source models, with notable strength in thinking-intensive tasks. These results highlight the value of specialized LLMs for domains demanding accuracy and interpretability, positioning Taramandal-GPT as a step toward reliable Artificial Intelligence (AI) assistants for astrophysics, spacecraft engineering, and space exploration.