登录 注册
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
👁 131 📚 5
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
👁 173 📚 11
TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
👁 123 📚 21
An Agentic Approach for Active 数据 (Data) Collection, Travel Behavior 模型 (Model)ing, and Weather-Sens...
An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Dema...
👁 81 📚 12
G-CARL: Grounded Checklist-Aligned Reward 学习 (Learning) for Patient-Oriented Medical Report Interpre...
G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretatio...
👁 131 📚 18
ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language 模型 (Model)s
ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models
👁 47 📚 28
SPADE: Self-Play in Adaptive Synthetic Executable Environments
👁 151 📚 21
Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiol...
👁 169 📚 9
Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
👁 155 📚 12
Split the Labor: Separating Evidence Interpretation from Decision Aggregation
👁 47 📚 6
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
👁 141 📚 23
AutoDesign: Meta-Harness 优化 (Optimization) for Long-Horizon Agentic Design
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
👁 60 📚 1
AVA-Encoder: Towards Agent-Native Video Representation 学习 (Learning)
AVA-Encoder: Towards Agent-Native Video Representation Learning
👁 129 📚 15
Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders
👁 205 📚 5
Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimension...
👁 104 📚 8
CreativeInstruct: Scalably Teaching LLMs to Balance Quality, Creativity, and Diversity
👁 52 📚 12
AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Informatio...
👁 184 📚 25
The Bitter Lesson of Tool Calling
👁 217 📚 21
Reasoning Core: Designing Broad Procedural 数据 (Data) for Completion-Supervised Reasoning Training
Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training
👁 121 📚 23
ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs
👁 147 📚 26
海洋智能体 🌊
海洋智能体
AI科研助手 · 3665篇文献
你好!你正在浏览文献列表,我可以帮你筛选方向、推荐高引论文或解读某个研究领域。