Agents

Research

scBench-Long: Verifiable Benchmarking of Long-Horizon Single-Cell Biology

Single-cell studies require analysts to convert raw measurements into specific biological claims through multi-step workflows and integration of metadata, assay…

2026-06-27

Research

Diagnosing Task Insensitivity in Language Agents

Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key source of thi…

2026-06-27

Practice

Securing agentic AI with perimeter guardrails: What's new in VPC Service Controls

As enterprises scale autonomous AI agents into production, enabling safe innovation requires robust architectural guardrails. AI agents connect across tools and…

2026-06-26

Practice

Production-grade AI agents for financial compliance: Lessons from Stripe

In this post, you learn how Stripe built a production-grade AI agent system for financial compliance. We cover the technical architecture of Stripe’s ReAct agen…

2026-06-26

Research

Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation

Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items. When an LRM get…

2026-06-26

Research

NeuraDock Visual Cognitive Load Agent Tutorial: A Quality-Gated Open-Source EEG Workflow for Alpha Dynamics and Real-Time Applications

This tutorial paper provides a step-by-step, reproducible walkthrough of NeuraDock Agent, an open-source EEG agent focused on Alpha dynamics and visual cognitiv…

2026-06-26

Research

SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills

Agents often repeatedly solve similar task instances from scratch, leading to unnecessary reasoning cost and long execution traces. Prior work has explored work…

2026-06-26

Research

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

While text-to-image (T2I) models have achieved remarkable progress, they struggle with real-world requests that are often underspecified, implicit, or dependent…

2026-06-26

Research

Parametric Open Source Games

Open-source game theory studies agents whose behavior may depend on one another's decision procedures, but most existing models use discrete or symbolic program…

2026-06-26

Research

OpenRCA 2.0: From Outcome Labels to Causal Process Supervision

Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. However, ex…

2026-06-26

Research

A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLO

We introduce the process harness, a new mechanism for uplifting legacy workflows into Agentic Business Process Management (Agentic BPM) without replacing the un…

2026-06-26

Briefing

General Intuition’s $2.3B bet that video games can train AI agents for the real world

General Intuition has raised $320 million to scale AI trained on millions of hours of gameplay, betting action data can help AI develop something closer to huma…

2026-06-25

Practice

Building agentic AI applications with a modern data mesh strategy on AWS

This post shows how to build a governed, serverless data mesh on AWS that provides the secure, scalable data foundation production agentic AI requires.…

2026-06-25

Practice

Build self-service AWS Health analytics to find actionable health insights with AI agents powered by Amazon Bedrock

In this post, we show you how to build Chaplin (Customer Health and Planned Lifecycle Intelligence Nexus), an open source solution that uses AI agents exposed t…

2026-06-25

Practice

Retrofit, don’t rebuild: Agentic overlays for transforming legacy enterprise services

In this technical collaboration between AWS and the authors, we present a pragmatic solution: agentic overlays. Agentic overlays are thin wrapper layers that tr…

2026-06-25

Briefing

Claude Code in Slack

a tip to get better UI from Codex…

2026-06-25

Briefing

Google bakes computer control directly into Gemini 3.5 Flash, letting the model see and operate your screen

Google has integrated "Computer Use" directly into Gemini 3.5 Flash, letting the model operate computers, browsers, and mobile devices on its own. On the OSWorl…

2026-06-25

Labs

How agents are transforming work

A new OpenAI research paper shows how AI agents are transforming work, enabling longer, more complex tasks and expanding productivity across roles.…

2026-06-25

Research

Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods

Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new …

2026-06-25

Research

Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention

Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context learning…

2026-06-25

Research

Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making

Recent studies on world modeling for Large Language Model (LLM) agents typically formulate the learning objective as next-observation prediction. However, this …

2026-06-25

Research

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where…

2026-06-25

Research

Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints

Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their interaction under joint deployment conditions remains insufficie…

2026-06-25

Research

UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving

Diffusion models have shown strong potential for multi-modal planning in end-to-end autonomous driving. However, most existing methods confine diffusion to the …

2026-06-25

Research

AI Snitches Get Glitches: Towards Evading Agentic Surveillance

To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs. Many employers (and e…

2026-06-25

Research

Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents

Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcom…

2026-06-25

Research

Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface

Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, including data-dri…

2026-06-25

Research

Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound

Multi-agent goal recognition asks an observer to jointly infer which agents act together and what each team is trying to achieve, so the hypothesis space grows …

2026-06-25

Research

Can Trustless Agents Be Trusted? An Empirical Study of the ERC-8004 Decentralized AI Agent Ecosystem

As autonomous AI agents increasingly transact across organizational boundaries, a fundamental trust challenge emerges: how can an agent assess whether an unknow…

2026-06-25

Research

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

For most of scientific history, researchers studying behavior could only infer hidden mechanisms from outward actions: an inverse problem that becomes more trac…

2026-06-25