全部收录论文
论文 · 第 132 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 132 / 141 页
查找论文请用站内搜索。
- Rethinking Deep Research from the Perspective of Web Content Distribution Matching
- UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking
- Amortizing Maximum Inner Product Search with Learned Support Functions
- Fine-Grained Table Retrieval Through the Lens of Complex Queries
- A Hybrid LTR-based System via Social Context Embedding for Recommending Solutions of Software Bugs in Developer Communities
- A Dynamic Self-Evolving Extraction System
- Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval
- SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans
- DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation
- SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
- Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
- ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
- Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
- SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
- In-Context Reinforcement Learning for Tool Use in Large Language Models
- RAVine: Reality-Aligned Evaluation for Agentic Search
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
- Scalable Training of Mixture-of-Experts Models with Megatron Core
- LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
- Deterministic Differentiable Structured Pruning for Large Language Models
- FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
- vLLM Hook v0: A Plug-in for Programming Model Internals on vLLM
- DOPD: A Dynamic PD-Disaggregation Architecture for Maximizing Goodput in LLM Inference Serving
- ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs
- Scaling Embeddings Outperforms Scaling Experts in Language Models
- Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment
- MoE Lens -- An Expert Is All You Need
- RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference
- Efficient Vector Search in the Wild: One Model for Multi-K Queries
- AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation
- MoEless: Efficient MoE LLM Serving via Serverless Computing
- Diffusion Language Models Are Natively Length-Aware
- NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches
- Balancing Domestic and Global Perspectives: Evaluating Dual-Calibration and LLM-Generated Nudges for Diverse News Recommendation
- MLLMRec-R1: Incentivizing Reasoning Capability in Large Language Models for Multimodal Sequential Recommendation
- Learning Next Action Predictors from Human-Computer Interaction
- ChatShopBuddy: Towards Reliable Conversational Shopping Agents via Reinforcement Learning
- Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions
- Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
- Stem: Rethinking Causal Information Flow in Sparse Attention
- Structured Multidimensional Representation Learning for Large Language Models
- Query Rewriting via LLMs
- COMI: Coarse-to-fine Context Compression via Marginal Information Gain
- Sensitivity-Aware Retrieval-Augmented Intent Clarification
- Visual Words Meet BM25: Sparse Auto-Encoder Visual Word Scoring for Image Retrieval
- DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
- GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search
- LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation
- Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis
- InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning