# MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval

arXiv: https://arxiv.org/abs/2605.06132 · HTML: https://mlsanity.com/paper/2605.06132/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

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

- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [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)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026)
- [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025)
- [Memory3: Language Modeling with Explicit Memory](https://mlsanity.com/paper/2407.01178/) (2024)
- [HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance](https://mlsanity.com/paper/2407.06937/) (2024)
- [zELO: ELO-inspired Training Method for Rerankers and Embedding Models](https://mlsanity.com/paper/2509.12541/) (2025)
- [BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation](https://mlsanity.com/paper/2508.06781/) (2025)

## Built on by (most cited first, 7 of 7)

- [LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation](https://mlsanity.com/paper/2608.12990/) (2026)
- [OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation](https://mlsanity.com/paper/2606.17628/) (2026)
- [GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory](https://mlsanity.com/paper/2608.26983/) (2026)
- [When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model](https://mlsanity.com/paper/2609.34227/) (2026)
- [UpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval](https://mlsanity.com/paper/2609.36805/) (2026)
- [Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives](https://mlsanity.com/paper/2610.01118/) (2026)
- [Recall What Is Missing: Composing Evidence from Long-Term Agent Memory](https://mlsanity.com/paper/2610.15642/) (2026)

## Abstract (arXiv)

In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage paradigm, but generic reranking models rely on semantic similarity matching and lack genuine reasoning capabilities, leading to a problem where recalled results are semantically highly relevant yet do not contain the key information needed to answer the question. This deficiency manifests in memory scenarios as three specific problems. First, relevance scores are miscalibrated, making threshold-based filtering difficult. Second, ranking degrades when facing temporal constraints, causal reasoning, and other complex queries. Third, the model cannot leverage dialogue context for semantic disambiguation. This report introduces MemReranker, a reranking model family (0.6B/4B) built on Qwen3-Reranker through multi-stage LLM knowledge distillation. Multi-teacher pairwise comparisons generate calibrated soft labels, BCE pointwise distillation establishes well-distributed scores, and InfoNCE contrastive learning enhances hard-sample discrimination. Training data combines general corpora with memory-specific multi-turn dialogue data covering temporal constraints, causal reasoning, and coreference resolution. On the memory retrieval benchmark, MemReranker-0.6B substantially outperforms BGE-Reranker and matches open-source 4B/8B models as well as GPT-4o-mini on key metrics. MemReranker-4B further achieves 0.737 MAP, with several metrics on par with Gemini-3-Flash, while maintaining inference latency at only 10--20% of large models. On finance and healthcare vertical-domain benchmarks, the models preserve generalization capabilities on par with mainstream large-parameter rerankers.