PairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Use
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/QwenLM/Qwen3.8
Terminology
Sources
- HaluMem: Evaluating Hallucinations in Memory Systems of Agents
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- MemR$^3$: Memory Retrieval via Reflective Reasoning for LLM Agents
- How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
- HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
- Mitigating Over-Personalization in LLMs via Structured Memory
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
- Memory in the Age of AI Agents
- CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions
- LongLaMP: A Benchmark for Personalized Long-form Text Generation
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection
- Choosing How to Remember: Adaptive Memory Structures for LLM Agents
- CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs
- Kimi K3: Open Frontier Intelligence
- MemGPT: Towards LLMs as Operating Systems
- Generative Agents: Interactive Simulacra of Human Behavior
- PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
- Zep: A Temporal Knowledge Graph Architecture for Agent Memory
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems