agents

arXiv:2606.04433v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in

arXiv:2606.05043v1 Announce Type: new Abstract: The last few years have witnessed major advances in the modeling and implementation of multiagent systems based on declarative interaction protocols. Ou

arXiv:2602.01619v2 Announce Type: replace-cross Abstract: Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards. One of the most co

This is the enterprise-agent security frame I like: treat agents like untrusted developers. They need the ability to call an API, not possession of the credential. Control plane outside runtime. Fail

arXiv:2606.04743v1 Announce Type: cross Abstract: Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface on

arXiv:2512.04668v4 Announce Type: replace-cross Abstract: Graph topology is a fundamental determinant of memory leakage in multi-agent LLM systems, yet its effects remain poorly quantified. We introdu

arXiv:2602.14117v2 Announce Type: replace-cross Abstract: Open Radio Access Networks (O-RAN) promise flexible 6G network access through disaggregated, software-driven components and open interfaces, b

arXiv:2606.04421v1 Announce Type: new Abstract: Many current agentic systems and LLM pipelines correct mistakes by optimizing outcome reward. This addresses only the what of failure: when an outcome d

arXiv:2510.27191v5 Announce Type: replace-cross Abstract: Planning under partial observability is an essential capability of autonomous robots. The Partially Observable Markov Decision Process (POMDP)

We have a Fleet agent called @docs_plz in our Slack that's made a very noticeable impact on our velocity of docs changes. In the chart below, you can clearly see that after it was added, the amount of

We partnered with Shopify so you can go from idea to live store in minutes Just tell Replit Agent what you want to sell. It will: - Build a custom storefront - Create your Shopify store - Help you add

we're taking an early bet on open models specifically, because they're SO much cheaper one point of reference: an app outputting 10M tokens/day costs roughly 250/day on Opus 4.8 versus ~24/day for Min

⚠️Why didn’t the hyperscalers wait until after the IPO in switching to pay-by-usage-charging? My guess is that *they literally could not afford to* —because it would bankrupt them. My reasoning: in “a

Agentic AI is making the semantic layer an essential enterprise priority because headless agents asking thousands of questions simultaneously have zero tolerance for inconsistent data definitions. Thi

arXiv:2606.03867v1 Announce Type: cross Abstract: Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data. Existing approaches oft

arXiv:2606.02871v1 Announce Type: cross Abstract: Large reasoning models improve performance by generating extended chain-of-thought (CoT) reasoning, but this behavior becomes inefficient when applied

This article describes how to integrate Model Context Protocol (MCP) tools with Reachy Mini, a small humanoid robot platform. It likely covers the technical steps for extending Reachy Mini's capabilit

arXiv:2606.03965v1 Announce Type: cross Abstract: Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little

At @harvey, the engineering team integrated Spectre — their internal background agent — into Devin Desktop. Now Spectre's organizational context can live on every engineer's laptop and flow across the

arXiv:2606.03664v1 Announce Type: cross Abstract: Ultra Reliable and Low Latency Communications (URLLC) was one of the main motivations behind 5G, with 3GPP advertising 1-10 ms latency targets for app

arXiv:2511.02304v2 Announce Type: replace-cross Abstract: We study learning multi-task, multi-agent policies for cooperative, temporal objectives, under centralized training, decentralized execution.

arXiv:2606.03340v1 Announce Type: new Abstract: Libraries require autonomous robots to move quietly through narrow aisles while remaining safe around readers, chairs, bags, and carts. This paper prese

arXiv:2606.03223v1 Announce Type: cross Abstract: Robot storytelling offers a unique blend of technological innovation and creative expression that engages children in unprecedented ways. However, the

Devin Desktop now supports Agent Control Protocol (ACP), allowing users to integrate their preferred AI agents into the platform. This feature enables users to bring custom or third-party agents into

9 min read · June 3, 2026 · Sebastian Kohlmeier Shipping an AI agent is the easy part. Keeping it accurate, safe, and accountable in production is where teams get stuck. Agents are non-deterministic.

Azure Content Understanding (CU) in Foundry Tools is Microsoft’s comprehensive content AI service. It ingests diverse data types — documents, audio, images, and video — and extracts the most critical

arXiv:2606.03034v1 Announce Type: cross Abstract: Large language model (LLM) agents have begun to delegate work to one another. Protocols such as the Model Context Protocol (MCP) and the Agent2Agent p

arXiv:2606.02641v1 Announce Type: cross Abstract: Interactive driving exposes a failure mode that is easy to miss in rule-aware autonomous-driving stacks: a hard-rule margin can be negative for an ego

Chopped it up with @swyx on @latentspacepod and we ran the gamut on this one. We talked platform, how roles are evolving, the agentic era, the future of open source, and what we’re building next. Spoi

arXiv:2606.02618v1 Announce Type: cross Abstract: We present Cognitive Loop via In-Situ Optimization (CLIO), an agent that couples a continuously-updated belief-state graph with a recursive plan-then-

arXiv:2604.17708v2 Announce Type: replace Abstract: Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tas

arXiv:2602.20213v2 Announce Type: replace-cross Abstract: The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existi

arXiv:2509.08726v3 Announce Type: replace-cross Abstract: This paper focuses on the decentralized stochastic optimization problem f(mathbf{x})=frac{1}{m}sum_{i=1}^m f_i(mathbf{x}) over a connected net

arXiv:2606.03083v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents increasingly rely on memory to learn from experiences over continual interactions. However, storing experiences

arXiv:2606.03874v1 Announce Type: new Abstract: We present DyaPlex, a streaming, full-duplex speech-and-motion model designed for dyadic interaction. To capture the continuous and reciprocal nature of

dynamic DAG workflow from 2023 :) Hm, not exactly sure this new task at the end is helpful. Though, look! I added task dependencies, for tasks that need results from a specific task to execute. (Here,

arXiv:2606.03268v1 Announce Type: new Abstract: Dexterous manipulation learning has long been hindered by the high costs of data and training, as pure reinforcement learning typically requires large-s

arXiv:2606.02859v1 Announce Type: cross Abstract: How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedric

Engram, a product or feature from Weaviate, has reached general availability status, meaning it is now fully released and accessible to all users. This announcement likely details the capabilities of

arXiv:2606.03739v1 Announce Type: new Abstract: LLM pipelines waste substantial token budgets on low-information content: repeated context, verbose responses, and redundant boilerplate. We introduce E

arXiv:2606.03841v1 Announce Type: new Abstract: Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain funda

arXiv:2606.03108v1 Announce Type: new Abstract: Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, wher

arXiv:2606.03694v1 Announce Type: cross Abstract: To enable meaningful human-robot interaction (HRI), a robot must continuously assess engagement by consistently tracking users over time. State-of-the

arXiv:2606.03574v1 Announce Type: cross Abstract: This work proposes a novel solution to predict pulsar timing residuals with limited data, addressing the critical challenge of data scarcity across sp

arXiv:2606.03453v1 Announce Type: cross Abstract: Vulnerability disclosure volumes now far exceed organizational assessment capacity, yet three adjacent research communities (proof-of-concept generati

The past year was about building agents. The next year is about putting them to work. Organizations have moved quickly from experimenting with AI agents to building ones that perform complex business