Explore Franklin AI
Understand new AI research with readable explanations and links to the original papers.
Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows This paper identifies a critical governance failure in modern agent...
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents Current multi-agent systems often struggle because they treat the "router" (the...
Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data This paper introduces a new architecture designed to solve a fundamental limitation o...
Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments Language agents often struggle in complex, inte...
MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education is a new research effort designed to evaluate how well art...
The paper "Flag Game: A Toy Model for Mechanistic Swarm Interpretability" introduces a new framework to study how AI agents form and spread beliefs within a...
Function Lives Where Variance Doesn’t: Task-Weighted Charts of a Language Model’s Computation This research investigates a fundamental question in AI: how ma...
Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry Reasoning Multimodal Large Language Models (MLLMs) are inc...
Suppressed, Not Erased: A Representational Trace of Edited Facts Survives Even Weight-Free Knowledge Editing When researchers "edit" a language model to chan...
Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization...
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.
