全部收录论文
论文 · 第 98 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 98 / 141 页
查找论文请用站内搜索。
- DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
- OpenIIR: An Open Simulation Platform for Information Retrieval Research
- Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning
- TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
- Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
- What Parameter Golf taught us about AI-assisted research
- OpenZL: Using Graphs to Compress Smaller and Faster
- Migrating Data Ingestion Systems at Meta Scale
- How to Eliminate Pipeline Friction in AI Model Serving
- Introducing NVIDIA Fleet Intelligence for Real-Time GPU Fleet Visibility and Optimization
- To Redact, or not to Redact? A Local LLM Approach to Deliberative Process Privilege Classification
- Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting
- Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs
- Sanity Checks for Long-Form Hallucination Detection
- Complete Evidence Extraction with Model Ensembles: A Case Study on Medical Coding
- Global-local Spatial-temporal Aware Graph Attention Network for Network Traffic Forecasting
- Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings
- DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
- Can LLMs Take Retrieved Information with a Grain of Salt?
- LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentation
- Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
- Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
- Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
- Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
- InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
- Towards Closing the Autoregressive Gap in Language Modeling via Entropy-Gated Continuous Bitstream Diffusion
- SilverTorch: A Unified Model-based System to Democratize Large-Scale Recommendation on GPUs
- PRISM: Refracting the Entangled User Behavior Space for E-Commerce Search
- An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Bridging Textual Profiles and Latent User Embeddings for Personalization
- DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation
- SCASRec: A Self-Correcting and Auto-Stopping Model for Generative Route List Recommendation
- TRACE: Tourism Recommendation with Accountable Citation Evidence
- FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances
- SocialReasoning-Bench: Measuring whether AI agents act in users' best interests
- When Does Embedding Magnitude Matter? A Cross-Task Functional-Symmetry Framework
- IntentGrasp: A Comprehensive Benchmark for Intent Understanding
- WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems
- MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal
- Overview of the TREC 2025 RAGTIME Track
- Hunt Globally: Wide Search AI Agents for Drug Asset Scouting in Investing, Business Development, and Competitive Intelligence
- DisastRAG: A Multi-Source Disaster Information Integration and Access System Based on Retrieval-Augmented Large Language Models
- LLM-Based Agents for Competitive Landscape Mapping in Drug Asset Due Diligence
- ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation
- Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
- MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
- MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes
- A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
- GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations