全部收录论文

论文 · 第 102 页

共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 102 / 141 页

查找论文请用站内搜索。

  1. KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation2026-05-06 · AI 搜索
  2. 美团 LongCat-Flash-Thinking-2601 开源:Agentic Search、工具调用与并行推理实践2026-05-06 · 智能体搜索
  3. T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning2026-05-06 · 智能体搜索
  4. TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation2026-05-06 · 智能体搜索
  5. Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization2026-05-06 · 智能体搜索
  6. Building for the Rising Complexity of Agentic Systems with Extreme Co-Design2026-05-06 · 智能体搜索
  7. AcademiClaw: When Students Set Challenges for AI Agents2026-05-06 · 智能体搜索
  8. PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments2026-05-06 · 智能体搜索
  9. SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation2026-05-06 · 智能体搜索
  10. Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems2026-05-06 · 智能体搜索
  11. GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving2026-05-06 · 系统与索引
  12. SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters2026-05-06 · 系统与索引
  13. SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection2026-05-06 · 系统与索引
  14. Microsoft at NSDI 2026: Advances in large-scale networked systems2026-05-06 · 系统与索引
  15. The ATOM Report: Measuring the Open Language Model Ecosystem2026-05-06 · 系统与索引
  16. LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference2026-05-06 · 系统与索引
  17. KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs2026-05-06 · 系统与索引
  18. Predicting LLM Output Length via Token-Wise Probabilistic Modeling2026-05-06 · 系统与索引
  19. Mixture of Heterogeneous Grouped Experts for Language Modeling2026-05-06 · 系统与索引
  20. TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation2026-05-06 · 系统与索引
  21. Exploring LLM biases to manipulate AI search overview2026-05-05 · 生成式推荐
  22. A Survey of Reasoning-Intensive Retrieval: Progress and Challenges2026-05-05 · 生成式推荐
  23. Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation2026-05-05 · 生成式推荐
  24. Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation2026-05-05 · 生成式推荐
  25. Retrieval-Augmented Reasoning for Chartered Accountancy2026-05-05 · 生成式推荐
  26. Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding (EVICT)2026-05-05 · 生成式推荐
  27. Escaping Mode Collapse in LLM Generation via Geometric Regulation2026-05-05 · 生成式推荐
  28. Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines2026-05-05 · 生成式推荐
  29. Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale2026-05-05 · 个性化推荐
  30. DynamicPO: Dynamic Preference Optimization for Recommendation2026-05-05 · 个性化推荐
  31. Time-Interval-Aware Disentangled Expert Modeling for Next-Basket Recommendation2026-05-05 · 个性化推荐
  32. MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents2026-05-05 · 个性化推荐
  33. Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion2026-05-05 · 个性化推荐
  34. ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?2026-05-05 · 个性化推荐
  35. MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems2026-05-05 · 个性化推荐
  36. Constructing Commonsense Knowledge Graph for Persona Consistency2026-05-05 · 个性化推荐
  37. Qwen3-Embedding-8B: Open-source SOTA on MTEB with Matryoshka Representations2026-05-05 · AI 搜索
  38. ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking2026-05-05 · AI 搜索
  39. H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations2026-05-05 · AI 搜索
  40. Adapting MLLMs for Nuanced Video Retrieval2026-05-05 · AI 搜索
  41. Proceedings of the Workshop on Information Retrieval's Role in RAG Systems (IR-RAG 2025) @ SIGIR 20252026-05-05 · AI 搜索
  42. MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction2026-05-05 · AI 搜索
  43. RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners2026-05-05 · 智能体搜索
  44. Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions2026-05-05 · 智能体搜索
  45. Are You the A-hole? A Fair, Multi-Perspective Ethical Reasoning Framework2026-05-05 · 智能体搜索
  46. Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations2026-05-05 · 智能体搜索
  47. Budget-Aware Routing for Long Clinical Text2026-05-05 · 智能体搜索
  48. Optimize Supply Chain Decision Systems Using NVIDIA cuOpt Agent Skills2026-05-05 · 智能体搜索
  49. How OpenAI delivers low-latency voice AI at scale2026-05-05 · 智能体搜索
  50. Agentic AI for Substance Use Education: Integrating Regulatory and Scientific Knowledge Sources2026-05-05 · 智能体搜索