mlsanityData to 14 Oct 2026

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

arXiv 2609.24246 ↗First posted 21 Sep 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 7 of its 15 references that are in the map. First posted on arXiv 21 Sep 2026.

Builds on

7 of 15 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model23 May

Other references · 6

  1. 2017Attention Is All You Needcited by 60,361
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  4. 2021Building astroBERT, a language model for Astronomy & Astrophysicscited by 19
  5. 2024AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomycited by 6
  6. 2024Can AI Understand Our Universe? Test of Fine-Tuning GPT by Astrophysical Datacited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models
  2. 2024AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets
  3. 2025Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)
  4. 2025Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning
  5. 2026AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models
  6. 2026Can LLMs Do Rocket Science? Exploring the Limits of Complex Reasoning with GTOC 12
  7. 2024Designing an Evaluation Framework for Large Language Models in Astronomy Research
  8. 2023Harnessing the Power of Adversarial Prompting and Large Language Models for Robust Hypothesis Generation in Astronomy