# Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments

arXiv: https://arxiv.org/abs/2403.08593 · HTML: https://mlsanity.com/paper/2403.08593/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 50 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 13 of 13)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Holistic Evaluation of Language Models](https://mlsanity.com/paper/2211.09110/) (2022)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [TaskWeaver: A Code-First Agent Framework](https://mlsanity.com/paper/2311.17541/) (2023)
- [Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family](https://mlsanity.com/paper/2303.07992/) (2023)
- [Rethinking Tabular Data Understanding with Large Language Models](https://mlsanity.com/paper/2312.16702/) (2023)

## Built on by (most cited first, 27 of 27)

- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [A Survey of Large Language Models for Graphs](https://mlsanity.com/paper/2405.08011/) (2024)
- [Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering](https://mlsanity.com/paper/2404.14741/) (2024)
- [QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction](https://mlsanity.com/paper/2403.11886/) (2024)
- [Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models](https://mlsanity.com/paper/2410.08414/) (2024)
- [TrustUQA: A Trustful Framework for Unified Structured Data Question Answering](https://mlsanity.com/paper/2406.18916/) (2024)
- [BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning](https://mlsanity.com/paper/2502.16660/) (2025)
- [Temporal Knowledge Graph Question Answering: A Survey](https://mlsanity.com/paper/2406.14191/) (2024)
- [Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies](https://mlsanity.com/paper/2512.01970/) (2025)
- [Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQA](https://mlsanity.com/paper/2505.20971/) (2025)
- [Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration](https://mlsanity.com/paper/2508.15809/) (2025)
- [TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data](https://mlsanity.com/paper/2412.19544/) (2024)
- [Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2510.08825/) (2025)
- [Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation](https://mlsanity.com/paper/2510.09671/) (2025)
- [From Anchors to Answers: A Novel Node Tokenizer for Integrating Graph Structure into Large Language Models](https://mlsanity.com/paper/2410.10743/) (2024)
- [Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering](https://mlsanity.com/paper/2505.19410/) (2025)
- [Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs](https://mlsanity.com/paper/2606.03705/) (2026)
- [Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering](https://mlsanity.com/paper/2505.12662/) (2025)
- [Plan of Knowledge: Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering](https://mlsanity.com/paper/2511.04072/) (2025)
- [Self-Correction Distillation for Structured Data Question Answering](https://mlsanity.com/paper/2511.07998/) (2025)
- [Towards Automated Air Traffic Safety Assessment Around Non-Towered Airports Using Large Language Models](https://mlsanity.com/paper/2605.12332/) (2026)
- [Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning](https://mlsanity.com/paper/2508.17905/) (2025)
- [The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering](https://mlsanity.com/paper/2509.07399/) (2025)
- [Dual-Evolving Reinforcement Learning for Automated Reward Design](https://mlsanity.com/paper/2512.13399/) (2025)
- [Runtime Burden Allocation for Structured LLM Routing in Agentic Expert Systems: A Full-Factorial Cross-Backend Methodology](https://mlsanity.com/paper/2604.01235/) (2026)
- [CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning](https://mlsanity.com/paper/2606.02170/) (2026)
- [X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization](https://mlsanity.com/paper/2609.32993/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown potential in reasoning over structured environments, e.g., knowledge graph and table. Such tasks typically require multi-hop reasoning, i.e., match natural language utterance with instances in the environment. Previous methods leverage LLMs to incrementally build a reasoning path, where the LLMs either invoke tools or pick up schemas by step-by-step interacting with the environment. We propose Reasoning-Path-Editing (Readi), a novel framework where LLMs can efficiently and faithfully reason over structured environments. In Readi, LLMs initially generate a reasoning path given a query, and edit the path only when necessary. We instantiate the path on structured environments and provide feedback to edit the path if anything goes wrong. Experimental results on three KGQA and two TableQA datasets show the effectiveness of Readi, significantly surpassing previous LLM-based methods (by 9.1% Hit@1 on WebQSP, 12.4% on MQA-3H and 9.5% on WTQ), comparable with state-of-the-art fine-tuned methods (67% on CWQ and 74.7% on WebQSP) and substantially boosting the vanilla LLMs (by 14.9% on CWQ). Our code will be available on https://aka.ms/readi.