Peer-reviewed research, distilled weekly

Applied AI Research

Every edition breaks down a peer-reviewed paper into actionable strategy. No hype — just evidence from the world's leading labs.

Latest Edition

reinforcement-learningskill-libraryself-improving-agentstool-usesequential-rolloutGRPO

The AI Agent That Learns From Its Own Work

SAGE, a reinforcement learning framework from AWS and UW-Madison, trains AI agents to write and reuse programmatic skills across chains of related tasks, achieving 8.9% higher scenario completion than RL-without-skills baselines while using 59% fewer tokens.

March 29, 202611 min readRead article

Source Paper

Reinforcement Learning for Self-Improving Agent with Skill Library

Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong

University of Wisconsin–Madison; AWS Agentic AI (Amazon)

Previous Editions

multi-agentretrieval-augmented-generationenterprise-search

77% Win Rate. This Is the RAG Architecture Behind It.

Atlassian's ADORE framework replaces single-pass RAG pipelines with a multi-agent, evidence-audited research loop that achieves a 77% win rate against ChatGPT Deep Research on business consulting tasks and outperforms all competitors on the DeepResearch Bench.

Atlassian

March 29, 20269 minRead
ai-governancerisk-managementconstitutional-ai

Your AI Vendor Has a Governance Problem

A Carnegie Mellon study reveals that Anthropic's Claude fails key transparency, bias, and accountability benchmarks under the NIST AI Risk Management Framework and EU AI Act, exposing significant governance gaps that enterprise buyers must audit before deployment.

Carnegie Mellon University, School of Computer Science, Privacy Engineering

March 17, 202610 minRead
skill-orchestrationmulti-agentDAG-planning

Agent Skills Don't Compound. The Framework That Changes That.

AgentSkillOS shows that structured skill composition via tree-based retrieval and DAG orchestration dramatically outperforms flat skill provisioning, even when agents have access to identical tools.

Shanghai Artificial Intelligence Laboratory

March 17, 20268 minRead