mlsanityData to 14 Oct 2026

ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering

arXiv 2604.08999 ↗First posted 10 Apr 2026cs.CL cs.AI cs.LGcited by 0

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

Abstract (arXiv)

Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering, hindered by challenges such as structural neglect, representation gaps, and reasoning opacity. Existing serialization methods fail to capture explicit hierarchies and lack schema flexibility, while current tree-based approaches suffer from limited semantic adaptability. To address these limitations, we propose ASTRA (Adaptive Semantic Tree Reasoning Architecture) including two main modules, AdaSTR and DuTR. First, we introduce AdaSTR, which leverages the global semantic awareness of LLMs to reconstruct tables into Logical Semantic Trees. This serialization explicitly models hierarchical dependencies and employs an adaptive mechanism to optimize construction strategies based on table scale. Second, building on this structure, we present DuTR, a dual-mode reasoning framework that integrates tree-search-based textual navigation for linguistic alignment and symbolic code execution for precise verification. Experiments on complex table benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance.

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 29 of its 49 references that are in the map. First posted on arXiv 10 Apr 2026.

Builds on

29 of 49 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs16 Jan
  2. 2025RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models4 Sep
  3. 2025RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals21 May
  4. 2024PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables5 Dec
  5. 2024TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning18 Sep
  6. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding9 Jan
  7. 2023Rethinking Tabular Data Understanding with Large Language Models27 Dec

Other references · 22

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  7. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  8. 2024DeepSeek-V3 Technical Reportcited by 811
  9. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 372
  10. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  11. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 137
  12. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
10 more
  1. 2023ReAcTable: Enhancing ReAct for Table Question Answeringcited by 76
  2. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 72
  3. 2023Table-GPT: Table-tuned GPT for Diverse Table Taskscited by 69
  4. 2024Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answeringcited by 25
  5. 2025TableMaster: A Recipe to Advance Table Understanding with Language Modelscited by 18
  6. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 16
  7. 2025ST-Raptor: LLM-Powered Semi-Structured Table Question Answeringcited by 11
  8. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challengescited by 10
  9. 2025Table as a Modality for Large Language Modelscited by 7
  10. 2026Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding
  2. 2025TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answering
  3. 2026H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning
  4. 2026MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
  5. 2025TableReasoner: Advancing Table Reasoning Framework with Large Language Models
  6. 2026PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding
  7. 2026IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Models
  8. 2026Orthogonal Hierarchical Decomposition for Structure-Aware Table Understanding with Large Language Models