# Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering

arXiv: https://arxiv.org/abs/2609.12230 · HTML: https://mlsanity.com/paper/2609.12230/

## 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 15 of its 71 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph](https://mlsanity.com/paper/2307.07697/) (2023)
- [Teaching Large Language Models to Reason with Reinforcement Learning](https://mlsanity.com/paper/2403.04642/) (2024)
- [Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need](https://mlsanity.com/paper/2507.13966/) (2025)
- [The Illusion of Readiness in Health AI](https://mlsanity.com/paper/2509.18234/) (2025)
- [GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation](https://mlsanity.com/paper/2505.20416/) (2025)
- [Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning](https://mlsanity.com/paper/2601.15160/) (2026)
- [Context Graph](https://mlsanity.com/paper/2406.11160/) (2024)
- [MedHopQA: A Disease-Centered Multi-Hop Reasoning Benchmark and Evaluation Framework for LLM-Based Biomedical Question Answering](https://mlsanity.com/paper/2605.12361/) (2026)
- [LLM-Guided Monte Carlo Tree Search over Knowledge Graphs: Composing Mechanistic Explanations for Drug-Disease Pairs](https://mlsanity.com/paper/2605.09542/) (2026)
- [Knowledge Graph-Driven Expert-Level Reasoning for Neuroscience](https://mlsanity.com/paper/2605.25183/) (2026)
- [Travel-Oriented Reasoning Large Language Model via Domain-Specific Knowledge Graphs](https://mlsanity.com/paper/2606.29254/) (2026)

## Abstract (arXiv)

Question-answering often requires reasoning across multiple connected facts rather than retrieving a single isolated relation. Knowledge graphs (KGs) provide a structured way to represent such facts, but training large language models (LLMs) only on isolated KG head-relation-tail triples may limit their ability to learn the surrounding context needed for multi-hop reasoning. In this work, we propose a context-augmented training framework for multi-hop question-answering. Although generally applicable, we validate the framework in the context of disease-specific KGs, extracted using a reliable KG extraction framework called GraphMERT, for Gastroparesis and Diabetes. For each primary KG triple, we attach supporting triples extracted from the same source text chunk to form a context graph (CG). This creates two supervision settings: KG-grounded supervision, which uses only the target KG triple or path, and CG-grounded supervision, which uses the target KG triple or path together with supporting context triples. We train the Qwen3-14B model using supervised fine-tuning (SFT) under both settings, producing KGModel and CGModel variants. To strengthen the lower-hop factual foundation of the models, we introduce an LLM-judged, history-aware adaptive repair pipeline that identifies unresolved one-hop failures, continually fine-tunes on targeted repair examples, and removes or quarantines problematic noisy triples. This repair stage enables the models to reach 100% accuracy on the cleaned retained one-hop validation sets. Finally, we employ reinforcement learning (RL) using lower-hop question-answer items and evaluate generalization on harder 3-hop, 4-hop, and 5-hop tasks. Across both diseases, context-augmented supervision consistently improves multi-hop performance over KG-only supervision. RL initialized from repaired SFT checkpoints yields larger and more stable gains.