Aug 20, 2026
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery introduces a system designed to solve complex, long-horizon scientific tasks by dy...
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Aug 20, 2026
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication introduces Verifiable Latent Alignments (VLA), a framework designed...
Aug 20, 2026
Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering
Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering proposes a framework for managing AI assistants by treating them...
Aug 20, 2026
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems argues that current AI benchmarks focus on the wrong metric...
Aug 20, 2026
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk addresses the challenge of how an agent should balance cautio...
Aug 20, 2026
Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering
Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering introduces a multi-agent framework designed to improve the accuracy and reli...
Aug 20, 2026
Breaking the weakest link to evade vision language models
Breaking the weakest link to evade vision language models investigates how adversarial perturbations—small, human-imperceptible changes to an image—can be us...
Aug 20, 2026
A Theory of Post-hoc Debate Judgement
A Theory of Post-hoc Debate Judgement proposes a formal framework to evaluate how AI agents should resolve debates.
Aug 20, 2026
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
Valentin Romanov, Monique Bax, and Steven Niederer investigate how frontier, browser-based large language models (LLMs) can be used to extract nuanced, conte...
Aug 20, 2026
What is Missing from AI Post-Training AI: An Empirical Analysis
This paper investigates the limitations of current AI agents in the context of "AI-for-AI," specifically focusing on their ability to perform end-to-end post...
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.