[ICML 2026] HEARTS: Benchmarking LLM Reasoning on Health Time Series

Live Deep Research Bench. A challenging, objective benchmark for deep research tasks.

Agentic AI refers to AI systems capable of autonomous decision-making, planning, and executing tasks based on goals—acting like intelligent agents. These systems combine LLMs with tools, memory, and feedback loops to complete complex workflows with minimal human input.

A benchmark for evaluating advanced reasoning in language models and multi-agent systems.

A symbolic reasoning framework using Cognitive Motifs to build diverse, interpretable, and belief-driven generative agents.

Multi-agent AI reporting readiness certification system for the Microsoft Agents League Reasoning Agents track.

LangGraph is a powerful framework built on LangChain that enables the creation of stateful, multi-step, and agentic workflows using directed graphs. It simplifies complex LLM orchestration by allowing conditional branching, memory, and tool integrations in a visual and modular way.

DELPHAI - multi-agent certification-readiness council on Microsoft Foundry (Agents League Battle #2). Real Foundry IQ on Azure AI Search, 11 hosted agents, GO/NEGOTIATE/NO-GO.

Seven-agent AI system for multi-scenario certification lab recovery, readiness insights, and safety-verified reports.

Microsoft Foundry IQ-powered AI governance agent for BFSI, detecting Logic Drift and enforcing HOTL governance. Currently in prototype build phase.

Docvoxia: Real-Time Multilingual Clinical Reasoning Agent for Safe Healthcare Documentation

🧠 A Streamlit app that evaluates and visualizes reasoning trajectories of AI agents — built with Python and inspired by agentic AI workflows, reasoning analysis, and LLM evaluation.

Microsoft Agents League hackathon project: a healthcare pathway reasoning agent that analyses simulated patient pathway data, identifies operational risks, recommends actions, and generates structured escalation notes.

Enterprise role-readiness agent on Microsoft Foundry. Pick a role, take a mock assessment, get a Foundry IQ grounded learning plan to close your skill gaps.

Multi-agent retail promotion-pricing system that recommends the profit-optimal discount with full reasoning — Azure AI Foundry + Foundry IQ grounding.

Intercepts an AI agent's action before it runs, grounds it in cited precedent via Foundry IQ, pauses for a human.

Point-of-care medication decision support — cited, triaged, grounded. Microsoft Agents League 2026 (Reasoning) on Microsoft Foundry IQ. Synthetic data only; not medical advice.

The False Readiness Firewall: Microsoft Agent Framework + Fabric IQ prove semantic conflicts with deterministic SQL, quantify learner and budget impact, and gate canonical meaning to the human owner.

Microsoft Foundry multi-agent certification coach for enterprise learning and workforce readiness.

⚖️ AI-powered reasoning agent that diagnoses the root causes of judicial backlog in Indian courts and recommends data-driven interventions using public judiciary datasets.