Meta-Reasoning Helps AI Agents Handle Longer Tasks
A new paper from researchers at Meta Superintelligence Labs proposes a different way to scale AI agents: instead of simply
Meta-Reasoning Helps AI Agents Handle Longer Tasks Read More »
Just-in-Time Memory: A New Approach to AI Agent Memory
Salesforce AI Research researchers have introduced Just-in-Time Memory, a new approach to long-term memory for AI agents that delays memory
Just-in-Time Memory: A New Approach to AI Agent Memory Read More »
SIFT Makes Self-Improving Coding Agents More Efficient
Researchers from MIT and Sakana AI have developed SIFT (Self-Improvement via Fast Tree-search), a framework designed to reduce the computational
SIFT Makes Self-Improving Coding Agents More Efficient Read More »
ScientistTwo Automates Autonomous AI Research
ScientistTwo, a new autonomous research framework from Google Cloud AI Research and collaborators at the University of Waterloo, is designed
ScientistTwo Automates Autonomous AI Research Read More »
Spatial-TTT: AI Framework for Streaming 3D Spatial Memory
Researchers have developed Spatial-TTT, a brand new framework created to enhance the way artificial intelligence models process long video streams
Spatial-TTT: AI Framework for Streaming 3D Spatial Memory Read More »
GigaTIME Multimodal AI Converts Pathology Slides to Proteomics
Microsoft researchers have released GigaTIME multimodal AI, a brand new artificial intelligence platform that is designed to transform routine pathology
GigaTIME Multimodal AI Converts Pathology Slides to Proteomics Read More »
SWE-CI Benchmark Tests AI Coding Agents in Real CI Workflows
A new research SWE-CI benchmark offers an improved method for assessing AI software developers by evaluating their ability to maintain
SWE-CI Benchmark Tests AI Coding Agents in Real CI Workflows Read More »
NVIDIA SideQuest: Smarter KV Cache Management for Long-Running AI Agents
Long-running agents, such as deep-research agents, must make multi-hop decisions across numerous documents and extended dialogues. As these tasks become more
NVIDIA SideQuest: Smarter KV Cache Management for Long-Running AI Agents Read More »
AI Fluency Index Explained: Measuring Human-AI Collaboration
The AI Fluency Index is a new research framework created by Anthropic to assess how well humans cooperate with AI
AI Fluency Index Explained: Measuring Human-AI Collaboration Read More »
Persona Selection Model: Why AI Assistants Seem Human?
AI-powered assistants like Claude may appear strangely human, communicating frustration, excitement and self-referential ideas. According to new research by Anthropic and
Persona Selection Model: Why AI Assistants Seem Human? Read More »