全部收录论文
论文 · 第 55 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 55 / 141 页
查找论文请用站内搜索。
- Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events
- Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
- Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control
- AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models
- Model ML completes finance work more efficiently with GPT-5.6 Sol
- Autonomy-of-Heads: Data-Free Sparse Attention from Frozen Query-Key Geometry
- BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization
- BROS: Efficient LLM Serving on Hybrid Real-time and Best-effort Requests
- FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
- TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation
- Lost in Interpolation: Why Predictive Feedback Fails in Diffusion Language Models
- GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization
- Simple-OPD: Demystifying Warm-up for On-policy Distillation
- OpenAI’s letter to Governor Abbott on responsible AI infrastructure in Texas
- From Understanding to Action: Feedback-Grounded Policy Discovery for Generative Recommendation
- Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation
- LoopMemGR: From Behavior Logs to Evolving Memory for Generative Recommendation
- MTGR:美团外卖生成式推荐Scaling Law落地实践
- Hierarchical Latent Reasoning for LLM-based Recommendation
- RecoReward: Recommender-Guided Multimodal Description Generation for Recommendation
- Auditing Semantic Gains in Sequential Recommendation: A Lightweight Recovery Test
- Cautious Context Steering for Language Model Personalization
- Shared-account recommendation with mixture-of-experts
- A New Role for Relevance: Guiding Corpus Interaction in Agentic Search
- SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation
- EfficientTool: A Cost-Effective Aligning Framework for Tool-Conditioned Agents in SME Scenarios
- CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
- AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
- When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents
- 阿里云AI搜索开放平台Agentic Search算法技术体系
- How HSP GRUPPE builds AI capabilities for tax advisory
- Responding to the next frontier of critical cyber capabilities
- Expressive Temporal Specifications for Reward Monitoring.
- La VIDA: Towards a Motivated Goal Reasoning Agent (Abstract Reprint).
- FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications
- SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
- MetaInfer: A Knowledge Only LLM Inference Engine Generator SKILL Toolbox
- ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU
- Recall Is Not Enough: A Reader-Context Diagnostic for Budget-Constrained Retrieval-Augmented Generation
- Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
- MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
- D$^2$F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation
- Document Optimization for Black-Box Retrieval via Reinforcement Learning
- ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
- MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding
- Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
- Generate Trajectories, Reasoning Traces, and Auto-Labels with NVIDIA Alpamayo 2 Super
- K-EXAONE 2.0 Technical Report
- Multi-Objective Ranking for Live-Streaming: Balancing Fresh and Delayed Signals with Segment-Aware Targeting
- LUCid: Redefining Relevance For Lifelong Personalization