# Joint Enhancement of Relational Reasoning for Long-Context LLMs

arXiv: https://arxiv.org/abs/2508.20351 · HTML: https://mlsanity.com/paper/2508.20351/

## Key facts

- Cited by 1 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 10 of its 53 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Yara Parser: A Fast and Accurate Dependency Parser](https://mlsanity.com/paper/1503.06733/) (2015)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Interpretable Contrastive Monte Carlo Tree Search Reasoning](https://mlsanity.com/paper/2410.01707/) (2024)
- [KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases](https://mlsanity.com/paper/2308.11761/) (2023)
- [On the Diagram of Thought](https://mlsanity.com/paper/2409.10038/) (2024)
- [CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph](https://mlsanity.com/paper/2406.17231/) (2024)

## Built on by (most cited first, 1 of 1)

- [Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning](https://mlsanity.com/paper/2606.11853/) (2026)

## Abstract (arXiv)

Despite significant progress, large language models (LLMs) still struggle with long contexts due to memory limitations and their inability to tackle complex and long-context tasks. Additionally, LLMs often suffer from a lack of transparency and are prone to producing hallucinations. To address these challenges, we propose JERR, a novel framework designed to enhance long-context comprehension via graph-based reasoning in LLMs. JERR integrates three key components: synopsis extraction, graph construction, and relational reasoning. First, synopsis is extracted by chunking text strategically, allowing the model to summarize and understand information more efficiently. Second, we build a directed acyclic graph (DAG) to resolve redundancy, ensuring logical consistency and clarity. Finally, we incorporate Monte Carlo Tree Search (MCTS) to help the model navigate complex reasoning paths, ensuring more accurate and interpretable outputs. This framework provides a novel solution that enables LLMs to handle extended contexts and complex reasoning tasks with improved reliability and transparency. Experimental results show that JERR consistently outperforms all baselines on the ROUGE and F1 metrics, achieving the highest scores on the LLM-Rater evaluation.