Agents

Create

Agentic workflows no longer need a personal access token

You can now use GitHub Agentic Workflows with GitHub Actions’s built-in GITHUB_TOKEN. This means that you no longer need to create and store a personal ac…

2026-06-12

Create

GitHub Agentic Workflows is now in public preview

GitHub Agentic Workflows is now in public preview. With agentic workflows, you can automate reasoning-based tasks like issue triage, CI failure analysis, and do…

2026-06-12

Research

Sensible Agent: A framework for unobtrusive interaction with proactive AR agents

Human-Computer Interaction and Visualization…

2026-06-12

Research

Import AI 441: My agents are working. Are yours?

Plus: Corrupting AI systems with a poison fountain…

2026-06-12

Research

Import AI 443: Into the mist: Moltbook, agent ecologies, and the internet in transition

Plus, a story about agents corrupting other agents…

2026-06-12

Research

Import AI 447: The AGI economy; testing AIs with generated games; and agent ecologies

What might a superintelligence arcology be like?…

2026-06-12

Research

Import AI 448: AI R&D; Bytedance's CUDA-writing agent; on-device satellite AI

If Ukraine is the first major drone war, when will there be the first major AI war?…

2026-06-12

Research

GPT 5.4 is a big step for Codex

On evaluating and understanding the frontier of agents, and why I still turn to Claude.…

2026-06-12

Research

Import AI 453: Breaking AI agents; MirrorCode; and ten views on gradual disempowerment

Was fire equivalent to a singularity for people at the time?…

2026-06-12

Research

SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests

Using SocialReasoning Bench, we observed a stable pattern across models—agents execute competently, but fail to consistently improve the user’s position, even w…

2026-06-12

Research

MagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models

MagenticLite is an agentic system for small models that works across the browser and local file system in a single workflow. It combines specialized models and …

2026-06-12

Research

Data Formulator 0.7: AI-powered data analytics for enterprise data

Data Formulator introduces AI-powered analytics for enterprise data workflows. Data teams can easily bring enterprise data into an AI-ready workspace where user…

2026-06-12

Research

Agentic MPC for Semantic Control System Resynthesis

While MPC effectively handles structured, diverse, and low-level specifications, it lacks the capability to dynamically incorporate high-level contextual inform…

2026-06-12

Research

MiniPIC: Flexible Position-Independent Caching in <100LOC

Retrieval-augmented and agentic workloads repeatedly prefill recurring predictable structured inputs (which we call "spans") such as documents and code files. Y…

2026-06-12

Research

MemRefine: LLM-Guided Compression for Long-Term Agent Memory

Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and …

2026-06-12

Research

From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews s…

2026-06-12

Research

IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing

Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creating a mismat…

2026-06-12

Research

Adaptive Turn-Taking for Real-time Multi-Party Voice Agents

Turn-taking in multi-party spoken conversations remains a fundamental challenge for voice-based agents, particularly under dynamic floor competition and varying…

2026-06-12

Research

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized se…

2026-06-12

Research

Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided Dispatch

Dispatch in three-sided marketplaces provides a natural setting for reinforcement learning from world feedback: decisions are evaluated by delayed operational o…

2026-06-12

Research

Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks

Shielded reinforcement learning is typically presented as a runtime safety mechanism that compiles temporal-logic specifications into automata restricting an ag…

2026-06-12

Research

InterleaveThinker: Reinforcing Agentic Interleaved Generation

Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constr…

2026-06-12

Research

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, …

2026-06-12

Labs

Introducing EVMbench

OpenAI and Paradigm introduce EVMbench, a benchmark evaluating AI agents’ ability to detect, patch, and exploit high-severity smart contract vulnerabilities.…

2026-06-12

Labs

OpenAI announces Frontier Alliance Partners

OpenAI announces Frontier Alliance Partners to help enterprises move from AI pilots to production with secure, scalable agent deployments.…

2026-06-12

Labs

Why we no longer evaluate SWE-bench Verified

SWE-bench Verified is increasingly contaminated and mismeasures frontier coding progress. Our analysis shows flawed tests and training leakage. We recommend SWE…

2026-06-12

Labs

Pacific Northwest National Laboratory and OpenAI partner to accelerate federal permitting

OpenAI and Pacific Northwest National Laboratory introduce DraftNEPABench, a new benchmark evaluating how AI coding agents can accelerate federal permitting—sho…

2026-06-12

Labs

OpenAI and Amazon announce strategic partnership

OpenAI and Amazon announce a strategic partnership bringing OpenAI’s Frontier platform to AWS, expanding AI infrastructure, custom models, and enterprise AI age…

2026-06-12

Labs

Introducing the Stateful Runtime Environment for Agents in Amazon Bedrock

Stateful Runtime for Agents in Amazon Bedrock brings persistent orchestration, memory, and secure execution to multi-step AI workflows powered by OpenAI.…

2026-06-12

Labs

How Balyasny Asset Management built an AI research engine

By combining rigorous model evaluation, full-platform use of OpenAI, and agent workflows, Balyasny is reinventing investment research.…

2026-06-12