2026-03-11

AI每日新闻汇总存档

前往 AI新闻雷达 看每日更新 → 返回存档列表

MASEval: Extending Multi-Agent Evaluation from Models to Systems
未知来源
No summary
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
未知来源
No summary
Meissa: Multi-modal Medical Agentic Intelligence
未知来源
No summary
DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering
未知来源
No summary
RoboLayout: Differentiable 3D Scene Generation for Embodied Agents
未知来源
No summary
AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem
未知来源
No summary
LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems
未知来源
No summary
Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search
未知来源
No summary
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
未知来源
No summary
Real-Time Trust Verification for Safe Agentic Actions using TrustBench
未知来源
No summary
SciTaRC: Benchmarking QA on Scientific Tabular Data that Requires Language Reasoning and Complex Computation
未知来源
No summary
Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning
未知来源
No summary
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
未知来源
No summary
HMR-1: Hierarchical Massage Robot with Vision-Language-Model for Embodied Healthcare
未知来源
No summary
Interpretable Markov-Based Spatiotemporal Risk Surfaces for Missing-Child Search Planning with Reinforcement Learning and LLM-Based Quality Assurance
未知来源
No summary
Can LLM Aid in Solving Constraints with Inductive Definitions?
未知来源
No summary
A Dynamic Self-Evolving Extraction System
未知来源
No summary
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
未知来源
No summary
📚 返回存档列表  |  🏠 返回首页