Aug 26, 2026
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
CAFE (Coupled Agent–Feedback Evolution) is a framework designed to improve how search agents handle long-horizon tasks by integrating learnable, in-trajector...
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Aug 26, 2026
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses introduces Recuris, an architecture designed to improve how AI agents handle...
Aug 26, 2026
Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space Core
Strictly Causal Streaming Video Anomaly Detection with a Theoretically-Grounded State-Space Core introduces a method for detecting video anomalies in real-ti...
Aug 26, 2026
StarHarness: Evolving Harnesses with Stratified Search for Enterprise Environments
StarHarness is a framework designed to improve the performance of Large Language Model (LLM) agents in enterprise environments by evolving the "harness"—the...
Aug 26, 2026
SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL
SPO++ is a reinforcement learning method designed to improve the efficiency of training language-model agents for reasoning and tool use.
Aug 26, 2026
Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought
Right Diagnoses, Decorative Reasoning: A Perturbation Audit of Medical Chain-of-Thought investigates whether the reasoning chains produced by Large Language...
Aug 26, 2026
A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments
A Dual-Dimensional LLM Framework for Automated Item Incidental Content Similarity Analysis in Large-Scale Assessments introduces a method to identify and man...
Aug 26, 2026
Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA
Constrained Entity Selection under Partial Knowledge (CES-PK) is a framework designed to improve the accuracy of Large Language Model (LLM) responses in Know...
Aug 26, 2026
FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs
FedV-KGQA is a framework designed to enable multi-hop question answering over knowledge graphs that are distributed across different organizations.
Aug 26, 2026
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing
StepGuard is a guard model designed to improve the safety of LLM-based agents by auditing their actions at the step level.
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.