# Query-focused and Memory-aware Reranker for Long Context Processing

arXiv: https://arxiv.org/abs/2602.12192 · HTML: https://mlsanity.com/paper/2602.12192/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Builds on (most cited first, 30 of 34)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval](https://mlsanity.com/paper/2407.19669/) (2024)
- [Retrieval Head Mechanistically Explains Long-Context Factuality](https://mlsanity.com/paper/2404.15574/) (2024)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks](https://mlsanity.com/paper/2010.08240/) (2020)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [On the Theoretical Limitations of Embedding-Based Retrieval](https://mlsanity.com/paper/2508.21038/) (2025)
- [Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks](https://mlsanity.com/paper/2511.07025/) (2025)
- [ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability](https://mlsanity.com/paper/2508.07050/) (2025)
- [DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval](https://mlsanity.com/paper/2508.07995/) (2025)
- [KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model](https://mlsanity.com/paper/2506.20923/) (2025)
- [Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking](https://mlsanity.com/paper/2506.09944/) (2025)
- [DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels](https://mlsanity.com/paper/2409.02465/) (2024)
- [Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios](https://mlsanity.com/paper/2311.08154/) (2023)
- [Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning](https://mlsanity.com/paper/2601.04726/) (2026)
- [SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation](https://mlsanity.com/paper/2601.02744/) (2026)
- [TongSearch-QR: Reinforced Query Reasoning for Retrieval](https://mlsanity.com/paper/2506.11603/) (2025)
- [The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters](https://mlsanity.com/paper/2501.01705/) (2025)
- [SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension](https://mlsanity.com/paper/2508.01959/) (2025)

## Built on by (most cited first, 6 of 6)

- [SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval](https://mlsanity.com/paper/2603.15599/) (2026)
- [EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory](https://mlsanity.com/paper/2606.21649/) (2026)
- [Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.01302/) (2026)
- [Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall](https://mlsanity.com/paper/2605.04897/) (2026)
- [MiA-Signature: Approximating Global Activation for Long-Context Understanding](https://mlsanity.com/paper/2605.06416/) (2026)
- [InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval](https://mlsanity.com/paper/2608.04761/) (2026)

## Abstract (arXiv)

Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach provides a listwise solution that leverages the holistic information within the entire candidate shortlist during ranking. At the same time, it naturally produces continuous relevance scores, enabling training on arbitrary retrieval datasets without requiring Likert-scale supervision. Our framework is lightweight and effective, requiring only small-scale models, such as 3B parameters, to achieve strong performance. Extensive experiments demonstrate that our method outperforms existing state-of-the-art pointwise and listwise rerankers across multiple domains, including Wikipedia and long narrative datasets. It further establishes a new state-of-the-art on the LoCoMo benchmark, which assesses dialogue understanding and memory usage. We further demonstrate that our framework supports flexible extensions. For example, augmenting candidate passages with contextual information further improves ranking accuracy, while training attention heads from middle layers enhances efficiency without sacrificing performance.