Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It
Research
Research News
New papers, breakthroughs and academic AI research
Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining
Research
ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents
Research
Self-Evaluating Recursive Agents
Research
Agentic discovery of blood biomarker from distilled private health records
Research
MedImageOSWorld: Benchmarking GUI Agents for Medical Image Consoles
Research
MemTrace: State-Consistent Memory for Long-Horizon Coding Agents
Research
Belief-Trajectory Energy: Measuring the Path to a Prediction
Research
FORGE: Verification-Gated Behavioral Repair for Generative Language Models
Research
Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence
Research
From Memory to Guide: Spatio-Temporal Composer for Procedural Coding Memory
Research
How Much Do LLM-as-a-Judge Design Choices Matter? A Systematic Comparison of Prompt Designs, Rating Scales, and Models
Research