Metraipolis › archive › dc_f351dedad265
Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking — arXiv:2609.24246
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24246
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:50:07.595Z
- SHA-256 of the archived text
f40c8dc9cd2929375ca4950fc98929f238b7dc918f4336f12608583b19bc05f9- Stable URL of this page
https://metraipolis.com/documento/dc_f351dedad265
How to cite
Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking — arXiv:2609.24246 — arXiv (en), https://arxiv.org/abs/2609.24246 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f351dedad265 (Metraipolis archive dc_f351dedad265, sha256 f40c8dc9cd2929375ca4950fc98929f238b7dc918f4336f12608583b19bc05f9)
BibTeX
@misc{dcf351dedad265,
title = {Taramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking — arXiv:2609.24246},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24246},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f351dedad265; sha256 f40c8dc9cd2929375ca4950fc98929f238b7dc918f4336f12608583b19bc05f9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24246. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.24246 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:48:45.043Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).