{"list":"other","total":93,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2502.12110","title":"A-MEM: Agentic Memory for LLM Agents","created":"2025-02-17","cited_by_count":1063},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"2504.19413","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","created":"2025-04-28","cited_by_count":779},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2407.12784","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","created":"2024-07-17","cited_by_count":429},{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417},{"id":"2501.13956","title":"Zep: A Temporal Knowledge Graph Architecture for Agent Memory","created":"2025-01-20","cited_by_count":400},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"2410.02644","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","created":"2024-10-03","cited_by_count":369},{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280},{"id":"1603.06155","title":"A Persona-Based Neural Conversation Model","created":"2016-03-19","cited_by_count":223},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187},{"id":"1902.00098","title":"The Second Conversational Intelligence Challenge (ConvAI2)","created":"2019-01-31","cited_by_count":179},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155},{"id":"2601.02553","title":"SimpleMem: Efficient Lifelong Memory for LLM Agents","created":"2026-01-05","cited_by_count":149},{"id":"2402.09727","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","created":"2024-02-15","cited_by_count":146},{"id":"2503.03704","title":"Memory Injection Attacks on LLM Agents via Query-Only Interaction","created":"2025-03-05","cited_by_count":144},{"id":"2602.02474","title":"MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents","created":"2026-02-02","cited_by_count":142},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138},{"id":"2312.08358","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","created":"2023-12-13","cited_by_count":133},{"id":"2402.05133","title":"Personalized Language Modeling from Personalized Human Feedback","created":"2024-02-06","cited_by_count":132},{"id":"2601.03192","title":"MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory","created":"2026-01-06","cited_by_count":129},{"id":"2402.08925","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","created":"2024-02-14","cited_by_count":123},{"id":"2409.05591","title":"MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation","created":"2024-09-09","cited_by_count":119},{"id":"2407.04363","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","created":"2024-07-05","cited_by_count":102},{"id":"2308.08239","title":"MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation","created":"2023-08-16","cited_by_count":97},{"id":"2407.11016","title":"LongLaMP: A Benchmark for Personalized Long-form Text Generation","created":"2024-06-27","cited_by_count":97},{"id":"2512.18746","title":"MemEvolve: Meta-Evolution of Agent Memory Systems","created":"2025-12-21","cited_by_count":95},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87},{"id":"2601.01885","title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","created":"2026-01-05","cited_by_count":78},{"id":"2512.10696","title":"Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution","created":"2025-12-11","cited_by_count":73},{"id":"2601.10156","title":"ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback","created":"2026-01-15","cited_by_count":72},{"id":"2409.20296","title":"PersonalLLM: Tailoring LLMs to Individual Preferences","created":"2024-09-30","cited_by_count":60},{"id":"2406.14703","title":"Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics","created":"2024-06-20","cited_by_count":59},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59},{"id":"2312.10007","title":"Faithful Persona-based Conversational Dataset Generation with Large Language Models","created":"2023-12-15","cited_by_count":47},{"id":"2512.12818","title":"Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects","created":"2025-12-14","cited_by_count":44},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42},{"id":"2409.11901","title":"LLMs + Persona-Plug = Personalized LLMs","created":"2024-09-18","cited_by_count":32},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31},{"id":"2503.15463","title":"From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment","created":"2025-03-19","cited_by_count":30},{"id":"2504.14650","title":"A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents","created":"2025-04-20","cited_by_count":30},{"id":"2603.11619","title":"Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats","created":"2026-03-12","cited_by_count":29},{"id":"2501.04167","title":"Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation","created":"2025-01-07","cited_by_count":27},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27},{"id":"2403.04260","title":"Can Small Language Models be Good Reasoners for Sequential Recommendation?","created":"2024-03-07","cited_by_count":26},{"id":"2407.02477","title":"Understanding Alignment in Multimodal LLMs: A Comprehensive Study","created":"2024-07-02","cited_by_count":23},{"id":"2410.14479","title":"Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models","created":"2024-10-18","cited_by_count":22},{"id":"2601.04463","title":"Beyond Static Summarization: Proactive Memory Extraction for LLM Agents","created":"2026-01-08","cited_by_count":21},{"id":"2512.18950","title":"Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement","created":"2025-12-22","cited_by_count":20},{"id":"2602.02007","title":"Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation","created":"2026-02-02","cited_by_count":19},{"id":"2509.23519","title":"ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search","created":"2025-09-27","cited_by_count":18},{"id":"2601.10088","title":"State of AI: An Empirical 100 Trillion Token Study with OpenRouter","created":"2026-01-15","cited_by_count":18},{"id":"2505.18882","title":"Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach","created":"2025-05-24","cited_by_count":16},{"id":"2505.16557","title":"Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planning","created":"2025-05-22","cited_by_count":15},{"id":"2511.12960","title":"ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents","created":"2025-11-17","cited_by_count":15},{"id":"2405.06275","title":"Pruning as a Domain-specific LLM Extractor","created":"2024-05-10","cited_by_count":13},{"id":"2410.03198","title":"PersoBench: Benchmarking Personalized Response Generation in Large Language Models","created":"2024-10-04","cited_by_count":13},{"id":"2601.02744","title":"SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation","created":"2026-01-06","cited_by_count":12},{"id":"2406.17803","title":"Understanding the Role of User Profile in the Personalization of Large Language Models","created":"2024-06-22","cited_by_count":11},{"id":"2505.24846","title":"MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning","created":"2025-05-30","cited_by_count":11},{"id":"2601.12449","title":"AgenTRIM: Tool Risk Mitigation for Agentic AI","created":"2026-01-18","cited_by_count":11},{"id":"2509.16882","title":"Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation","created":"2025-09-21","cited_by_count":10},{"id":"2601.07470","title":"Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory","created":"2026-01-12","cited_by_count":10},{"id":"2507.18302","title":"LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models","created":"2025-07-24","cited_by_count":9},{"id":"2601.16621","title":"How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants","created":"2026-01-23","cited_by_count":9},{"id":"2509.17183","title":"LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization","created":"2025-09-21","cited_by_count":7},{"id":"2601.17887","title":"When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents","created":"2026-01-25","cited_by_count":7},{"id":"2412.09318","title":"Benchmarking LLMs for Mimicking Child-Caregiver Language in Interaction","created":"2024-12-12","cited_by_count":6},{"id":"2511.21460","title":"MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning","created":"2025-11-26","cited_by_count":6},{"id":"2505.09496","title":"Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data","created":"2025-05-14","cited_by_count":4},{"id":"2506.06970","title":"Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment","created":"2025-06-08","cited_by_count":4},{"id":"2411.10761","title":"Can Generic LLMs Help Analyze Child-adult Interactions Involving Children with Autism in Clinical Observation?","created":"2024-11-16","cited_by_count":3},{"id":"2412.11736","title":"Personalized LLM for Generating Customized Responses to the Same Query from Different Users","created":"2024-12-16","cited_by_count":2},{"id":"2509.03672","title":"SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences","created":"2025-09-03","cited_by_count":2},{"id":"2510.27016","title":"Semantically-Aware LLM Agent to Enhance Privacy in Conversational AI Services","created":"2025-10-30","cited_by_count":2},{"id":"2512.00804","title":"Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval","created":"2025-11-30","cited_by_count":2},{"id":"2603.22779","title":"KARMA: Knowledge-Action Regularized Multimodal Alignment for Personalized Search at Taobao","created":"2026-03-24","cited_by_count":2},{"id":"2508.08634","title":"Adaptive Personalized Conversational Information Retrieval","created":"2025-08-12","cited_by_count":1},{"id":"2508.14912","title":"Multimodal Recommendation via Self-Corrective Preference Alignmen","created":"2025-08-13","cited_by_count":1},{"id":"2509.08747","title":"Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity","created":"2025-09-03","cited_by_count":1},{"id":"2605.27805","title":"ChildEval: When large language models meet children's personalities","created":"2026-05-27","cited_by_count":1}],"next_cursor":null}