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。
- KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation
- 美团 LongCat-Flash-Thinking-2601 开源:Agentic Search、工具调用与并行推理实践
- T^2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
- TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation
- Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
- Building for the Rising Complexity of Agentic Systems with Extreme Co-Design
- AcademiClaw: When Students Set Challenges for AI Agents
- PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
- SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation
- Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems
- GhostServe: A Lightweight Checkpointing System in the Shadow for Fault-Tolerant LLM Serving
- SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
- SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
- Microsoft at NSDI 2026: Advances in large-scale networked systems
- The ATOM Report: Measuring the Open Language Model Ecosystem
- LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
- KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
- Predicting LLM Output Length via Token-Wise Probabilistic Modeling
- Mixture of Heterogeneous Grouped Experts for Language Modeling
- TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation
- Exploring LLM biases to manipulate AI search overview
- A Survey of Reasoning-Intensive Retrieval: Progress and Challenges
- Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
- Structure-Aware Chunking for Tabular Data in Retrieval-Augmented Generation
- Retrieval-Augmented Reasoning for Chartered Accountancy
- Making Every Verified Token Count: Adaptive Verification for MoE Speculative Decoding (EVICT)
- Escaping Mode Collapse in LLM Generation via Geometric Regulation
- Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
- Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale
- DynamicPO: Dynamic Preference Optimization for Recommendation
- Time-Interval-Aware Disentangled Expert Modeling for Next-Basket Recommendation
- MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
- Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion
- ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?
- MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
- Constructing Commonsense Knowledge Graph for Persona Consistency
- Qwen3-Embedding-8B: Open-source SOTA on MTEB with Matryoshka Representations
- ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking
- H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations
- Adapting MLLMs for Nuanced Video Retrieval
- Proceedings of the Workshop on Information Retrieval's Role in RAG Systems (IR-RAG 2025) @ SIGIR 2025
- MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction
- RSAT: Structured Attribution Makes Small Language Models Faithful Table Reasoners
- Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions
- Are You the A-hole? A Fair, Multi-Perspective Ethical Reasoning Framework
- Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations
- Budget-Aware Routing for Long Clinical Text
- Optimize Supply Chain Decision Systems Using NVIDIA cuOpt Agent Skills
- How OpenAI delivers low-latency voice AI at scale
- Agentic AI for Substance Use Education: Integrating Regulatory and Scientific Knowledge Sources