登录 注册
Automated Discovery Has No Universally Superior Harness
👁 173 📚 9
An Exam for Active Observers
👁 202 📚 13
Pretraining 数据 (Data) Can Be Poisoned through Computational Propaganda
Pretraining Data Can Be Poisoned through Computational Propaganda
👁 189 📚 16
SciDiagramEdit: 学习 (Learning) to Edit Scientific Diagrams from Paper Revisions
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
👁 54 📚 21
Partition, Prompt, Aggregate: 统计 (Statistical) Self-Consistency in Language 模型 (Model)s
Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models
👁 197 📚 23
Hindcast: Replaying 预测 (Prediction) Markets to Evaluate LLM Forecasters
Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters
👁 184 📚 14
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
👁 39 📚 10
Metacognition in LLMs: Foundations, Progress, and Opportunities
👁 168 📚 26
Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reason...
👁 64 📚 18
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
👁 179 📚 5
Validity of LLMs as data annotators: AMALIA on authority
👁 153 📚 13
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
👁 146 📚 9
Co-LMLM: Continuous-Query Limited Memory Language 模型 (Model)s
Co-LMLM: Continuous-Query Limited Memory Language Models
👁 83 📚 26
Rethinking Indic AI from a Lens of Cultural Heritage Preservation
👁 111 📚 4
Weak-to-Strong Generalization via Direct On-Policy Distillation
👁 89 📚 1
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
👁 111 📚 17
Measuring the Gap Between Human and LLM Research Ideas
👁 222 📚 22
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
👁 201 📚 25
Self-Evolving World 模型 (Model)s for LLM Agent Planning
Self-Evolving World Models for LLM Agent Planning
👁 51 📚 19
Towards Automating Scientific Review with Google's Paper Assistant Tool
👁 227 📚 14
海洋智能体 🌊
海洋智能体
AI科研助手 · 4376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。