Explore Franklin AI
Understand new AI research with readable explanations and links to the original papers.
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development Software development is a complex, multi-stage process that is incr...
Evidence-State Rewards for Long-Context Reasoning introduces Maven (Marginal-Value Evidence Navigation), a reinforcement learning framework designed to impro...
Evaluating large language model (LLM) agents is a significant bottleneck in AI development.
Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks As telecommunications networks move toward full autonomy, AI an...
Atomic Task Graph: A Unified Framework for Agentic Planning and Execution introduces a new way for AI agents to handle complex, multi-step tasks.
OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models Ontology learning (OL) is the process of automatically building struct...
Modern language models often personalize interactions by storing user information—such as age, occupation, or disability status—and injecting it into future...
Agentic systems—AI models that use external tools and persistent memory to complete tasks—are increasingly vulnerable to "poisoning" attacks.
Online Safety Monitoring for LLMs Large Language Models (LLMs) are increasingly used for critical tasks, yet they remain prone to generating harmful, incorre...
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think This paper addresses a critical failure in current AI training methods.
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.
