Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking

2026-09-21

AI Summary

为解决天体力学中多步推理和符号操作难题，本文提出Taramandal-GPT模型，通过增强知识检索和结构化思维提升问题解决能力。

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.

Problem

• large language models
• astrodynamics
• multi-step reasoning
• symbolic manipulation
• domain-specific terminology

Innovation

• Retrieval-Augmented Generation (RAG)
• fallback mechanism
• Astrodynamics Problems Benchmark (APBench)