Explore Franklin AI
Understand new AI research with readable explanations and links to the original papers.
Joint Learning of Experiential Rules and Policies for Large Language Model Agents Large Language Model (LLM) agents often struggle to improve in complex, mul...
Franklin AI Research Explainer: Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings As Large Langu...
Language-Based Digital Twins for Elderly Cognitive Assistance introduces a new way to monitor cognitive health by creating "digital twins"—virtual models tha...
AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems In modern industrial settings, improving recommendation algorithms is typically...
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text Deep learning models are increasingly used to analyze text, but they...
TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference Multimodal Large Language Models (M...
EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting Earth Observation (EO) forecasting aims to predict how the Earth's s...
Semantic Early-Stopping for Iterative LLM Agent Loops Multi-agent LLM systems, such as a "Writer" that drafts and a "Critic" that revises, typically rely on...
This paper introduces the "process harness," a new architectural mechanism designed to modernize legacy business workflows by integrating AI agents without r...
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems introduces a new architectural approach to AI safety.
Start with the overview to understand the paper’s main idea, then follow its original paper link for the methods, results and limitations.
Use Submit Research to send the original paper URL and explain why it is useful. An editor reviews the suggestion before publication.
