May 29, 2026
AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
AgentSchool is an LLM-powered multi-agent simulation platform designed to act as a "wind tunnel" for educational research.
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
May 29, 2026
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models Large language models are increasingly used for long, complex ta...
May 29, 2026
Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers
Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers Diffusion Transformers (DiTs) have become the standard for high-quality ima...
May 29, 2026
Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale
Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale This research explores how to effectiv...
May 29, 2026
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection Recent advancements in Vision-Language Models (VLMs) have transformed...
May 29, 2026
From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs Urban trajectory data is essential for smart city planning and tran...
May 29, 2026
BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders This research investigates whether language model...
May 29, 2026
PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers
PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers Poker is a notoriously difficult challenge for artificial intelligence, traditionall...
May 29, 2026
Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation
Evaluating interactive web code generated by AI has become a major challenge. Current methods often rely on rigid checklists or human-judged leaderboards, wh...
May 29, 2026
ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure
ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure Scientific discovery is a creative and uncertai...
Good to know
How do I use these AI research explainers?
Start with the overview to understand the paper’s main idea, then follow its original paper link for the methods, results and limitations.
Can I suggest a research paper?
Use Submit Research to send the original paper URL and explain why it is useful. An editor reviews the suggestion before publication.