全部收录论文
论文 · 第 79 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 79 / 141 页
查找论文请用站内搜索。
- Music Playlist Captioning at Scale with Large Language Models
- A Rank-One Popularity Component in Dot-Product Recommender Scores: Population Theory and Prior-Separation Evidence
- MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS
- KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
- Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model
- Improving Long-Context Retrieval with Multi-Prefix Embedding
- HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions
- Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
- When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG
- Multi-Vector Embeddings are Provably More Expressive than Single Vector Embeddings
- moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT
- Novelty-Aware Agentic Retrieval: Comparing Research Contributions Through Structured Multi-Step Reasoning
- From Embedding Geometry to Spectral Search: Energy Dispersion Networks For Vector Retrieval
- EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory
- DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks
- PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems
- Self-Compacting Language Model Agents
- Tmax: A simple recipe for terminal agents
- When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents
- Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
- Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
- CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
- Training Open Models for Agentic Phone Use
- Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search
- Intelligent Multimodal Retrieval and Reasoning for Geospatial Knowledge Discovery on the I-GUIDE Platform
- ScholarSum: Student-Teacher Abstractive Summarization via Knowledge Graph Reasoning and Reflective Refinement
- JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling
- Ensuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED
- Private Learning with Public Feature Conditioning
- The Illusion of Improvement: Reject Inference Strategies in Credit Scoring
- Zero-Shot Active Feature Acquisition via LLM-Elicitation
- E2Rank: Your Text Embedding can Also be an Effective and Efficient Listwise Reranker
- Scaling Laws for Cross-Encoder Reranking
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
- KuaiSearch: A Large-Scale E-Commerce Search Dataset for Recall, Ranking, and Relevance
- uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking
- Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents
- CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference
- Uncertainty Decomposition for Clarification Seeking in LLM Agents
- When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation
- Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose
- Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
- PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents
- ScaffoldAgent: Utility-Guided Dynamic Outline Optimization for Open-Ended Deep Research
- MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments
- ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments
- Lodestar: An Online-Learning LLM Inference Router
- Beyond Greedy Chunking: SLO-Aware Sliding-Window Scheduling for LLM Inference
- AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning