TRACE-Memory: Public-Conditioned Retrieval and Utility-Aware Evidence Admission for Personalized Generation
Jing Wang, Zhu Wang, Yifan Guo, Yulong Yang, Yunji Liang
cs.AI
Submitted: 2026-08-21
Updated: 2026-08-24
Comments: 9 pages, 4 figures, and 6 tables. Submitted to the 41st AAAI Conference on Artificial Intelligence (AAAI 2027)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Response-Aware User Memory Selection for LLM Personalization
- The Llama 3 Herd of Models
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
- OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
- LongLaMP: A Benchmark for Personalized Long-form Text Generation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Large Language Models Can Be Easily Distracted by Irrelevant Context
- C-Pack: Packed Resources For General Chinese Embeddings
- Qwen3 Technical Report
- Personalized Dialogue Generation with Diversified Traits
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