agents

arXiv:2604.27840v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have shown great promise in time series forecasting. However, most existing LLM-based forecasting methods still

arXiv:2504.12612v2 Announce Type: replace Abstract: Provenance is the chronological history of things, resonating with the fundamental pursuit to uncover origins, trace connections, and situate entiti

arXiv:2604.28043v1 Announce Type: new Abstract: We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific d

arXiv:2604.28138v1 Announce Type: cross Abstract: Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restor

create_agent - how we build Deep Agents on the simplest harness primitive underlying all of the harness engineering, research, and API design in Deep Agents is a very simple primitive in LangChain cal

deep agents need the web, and it’s super exciting to team up with @LangChain to make that happen! Build agents with LangChain + @browserbase. Give your Deep Agents search, fetch, and browser subagents

Cognition AI announced an integration of Devin, their AI coding assistant, directly into terminal/shell environments, accessible via a Ctrl+G keyboard shortcut that allows the AI to view the user's cu

arXiv:2604.28038v1 Announce Type: new Abstract: Purpose: Fast detection of plant stress is key to plant phenotyping, precision agriculture, and automated crop management. In particular, efficient irri

arXiv:2604.27092v1 Announce Type: new Abstract: Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods

arXiv:2604.27309v1 Announce Type: new Abstract: Clinical AI systems require not just point-in-time evaluation but continuous governance: the ongoing practice of monitoring, evaluating, iterating, and

Fleet can now generate and render SVGs and Mermaid diagrams inline! Ask it to make you a diagram, and watch it work its magic. I'm using a mix of our GitHub tools, and @cognition's DeepWiki to make th

arXiv:2604.27935v1 Announce Type: new Abstract: This paper presents an expert-guided active-inference-inspired framework for adaptive UAV swarm trajectory planning. The proposed method converts multi-

arXiv:2604.28057v1 Announce Type: new Abstract: As autonomous vehicles slowly deploy into urban roads for limited use cases with significant edge case issues, closed facilities like marshaling yards p

arXiv:2604.27660v1 Announce Type: new Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learn

Grok The new Grok-4.3 from @xai is live on OpenRouter! Grok-4.3 releases at a lower price than Grok-4.2, while seeing a large jump in agentic performance: a 321 point increase to 1500 ELO on @Artifici

arXiv:2604.27955v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents have emerged as a promising paradigm for intelligent systems that perceive and interact with graphical interfaces

here's a deep dive on how middleware lets you customize your agent harness, excellent writeup by @Vtrivedy10 !! deepagents offers a powerful base harness that you can customize for your use case! crea

arXiv:2604.27351v1 Announce Type: new Abstract: Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally

I have to go out of town for a funeral thru the weekend but I am leaving everyone with one new cool feature inspired by ralph loops and Codex's upcoming /goal feature. If you use /goal <prompt>, it wi

i said on @jacobeffron's pod recently that 'coding agents breaking containment' is the breakout theme of the year. i meant it - this is the year all knowledge workers, not just coders, get AGI-pilled.

Elon Musk highlighted agent mode on Grok Imagine as a significant advancement in generative AI applications. Agent mode appears to enable more autonomous and sophisticated capabilities for AI image ge

I'm trying to build an office receptionist app for my reachy mini today with ml intern + @OpenAI GPT 5.5. Wish me luck! You can follow my session agent traces live here: https://huggingface.co/dataset

arXiv:2512.17435v3 Announce Type: replace Abstract: Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent

arXiv:2501.19143v2 Announce Type: replace Abstract: As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial a

arXiv:2604.27891v1 Announce Type: new Abstract: Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator above the LLM, tracking

arXiv:2604.27156v1 Announce Type: new Abstract: Rational belief revision is commonly viewed as being based on a preference order between possible worlds, with the resulting new belief set being those

Is agent harness engineering the new prompt engineering? @LangChain co-founder and CEO, @hwchase17, joined us at #GoogleCloudNext to explain why the 'harness' is the secret to moving AI agents from a

It is honestly shocking how little code can get you so far within this base primitive. create_agent is one of the most fun things for me to show people who are trying to get started here - because it

arXiv:2604.27539v1 Announce Type: cross Abstract: As information ecosystems grow more heterogeneous, both humans and artificial agents increasingly face a simple yet unresolved question: when seeking

✈️ @LATAMAirlines is landing at Interrupt. The largest airline in Latin America built two production agents that handle trip planning and agency coordination. Building them was easy. Operating at scal

arXiv:2604.27821v1 Announce Type: new Abstract: Accurate localization is a fundamental requirement for autonomous robots operating in indoor environments. Scene graphs encode the spatial structure of

arXiv:2508.05469v3 Announce Type: replace Abstract: We evaluate artificial intelligence (AI) systems without ground truth by exploiting a link between strategic gaming and information loss. Building o

Jerry Liu considers whether llama_index should rebrand to 'applied automation co,' suggesting potential strategic discussions about the project's direction and positioning. This appears to be a casual

arXiv:2604.27297v1 Announce Type: new Abstract: Deriving governing equations from empirical observations is a longstanding challenge in science. Although artificial intelligence (AI) has demonstrated

many sensitive Agent Workloads today require some sort of human feedback LangGraph supplies the runtime primitives for LangChain + Deep Agents and makes it easy to durably pause, resume, and replay ag

Twitter said pick a side. The eval said the question was wrong. Six months ago, MCP (model context protocol) was the hot new thing: tool usage with a built-in discovery... The post MCP vs. CLI Skills

Microsoft is launching a new AI agent inside Word that's specifically designed for legal teams. Legal Agent handles document edits, negotiation history, and complex documents to help legal teams handl

arXiv:2604.27934v1 Announce Type: new Abstract: Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting sign

arXiv:2604.27872v1 Announce Type: new Abstract: Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumul

most of the time, you want an agent loop to run uninterrupted. that's where the utility comes from! but some decisions shouldn't be delegated to the agent. two situations come up consistently: 1/ befo

A user reported experiencing a false positive from their vehicle's driver monitoring system, which incorrectly detected their eyes as closed when they were actually open, prompting a humorous reaction

new mode for LangChain's human in the loop middleware: respond instead of running a tool, you can return the human's interrupt response directly as the tool's output handy for 'ask user' stubs or head

NEW paper from Microsoft Research. If you care about training computer-use agents, this is one to keep. (bookmark it) The team builds 1,000 synthetic computers (each with realistic directory structure

NEW paper: Recursive Multi-Agent Systems // Recursive Multi-Agent Systems // Great read for the weekend. (bookmark it) Multi-agent systems often pass full text messages between agents at every step. T

one future trend i'm very excited by: models getting good enough where they can power agents that browse the web deepagents + @browserbase is a glimpse of that future See the full example here: https:

One thing I love about LangChain is how the OSS pieces build on each other You can build robust workflows directly with LangGraph, our orchestration framework. We also use it as the foundation for Dee