Search: “agents”

arXiv:2606.00183v1 Announce Type: cross Abstract: Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, a

Snowflake Inc. is using its Summit 2026 conference today in San Francisco to present a vision of what it calls the “agentic enterprise,” unveiling a broad set of products and enhancements that it says

arXiv:2606.01961v1 Announce Type: new Abstract: Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form c

Amazon Web Services Inc. today enhanced its database services to simplify the process of building and operating agentic artificial intelligence applications while also lowering the barriers to cloud m

arXiv:2606.02109v1 Announce Type: new Abstract: Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approac

arXiv:2602.11790v2 Announce Type: replace Abstract: Although recent end-to-end video generation models demonstrate impressive performance in visually oriented content creation, they remain limited in

arXiv:2606.01166v1 Announce Type: cross Abstract: Computer-use agents extend language models from text generation to sustained interaction with files, terminals, browsers, and external tools. This shi

arXiv:2603.16572v2 Announce Type: replace-cross Abstract: Agent skills extend local AI agents, such as Claude Code and OpenClaw, with additional functionality. Their growing popularity has led to dedi

arXiv:2606.00096v1 Announce Type: cross Abstract: Visual agents employ external visual tools within visual chains of thought to incorporate fine-grained evidence. While prior work has mainly studied t

LangChain Labs is conducting research into developing more efficient verification systems for validating the outputs and work products of AI agents. This research likely focuses on improving the speed

Efficient verification is what makes scaling legal agents practical. Excited to partner with @hwchase17 and the @LangChain Labs team on designing efficient verifiers - sharing early results showing op

Mario Rodriguez / The GitHub Blog: GitHub unveils a GitHub Copilot desktop app in technical preview, which introduces a new feature called canvases for bidirectional work between users and agents — At

arXiv:2606.02449v1 Announce Type: new Abstract: Multimodal agents are increasingly expected to operate interfaces on behalf of users, raising a central deployment question: can they truly substitute f

arXiv:2606.00308v1 Announce Type: cross Abstract: Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestrations - analyst, coder, tester, and debugger pipel

Devin Desktop is a unified management interface from Cognition AI that enables users to coordinate multiple AI agents operating across local and cloud environments. The platform streamlines workflows

Microsoft Corp. announced an expansion to its artificial intelligence models and agentic AI infrastructure today that brings more data and context into the hands of developers and business users as th

arXiv:2606.02107v1 Announce Type: cross Abstract: This paper proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework for quadcopter consensus control. Compared to convent

arXiv:2604.03588v3 Announce Type: replace Abstract: AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting int

arXiv:2606.01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration to

arXiv:2606.02302v1 Announce Type: cross Abstract: Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabili

arXiv:2505.17648v5 Announce Type: replace-cross Abstract: We introduce a framework for simulating macroeconomic expectations in survey experiments using LLM-based economic agents (LLM Agents). We cons

arXiv:2606.02380v1 Announce Type: cross Abstract: As LLM-based agents expand their operational scope, reliability becomes a prerequisite for real-world deployment. However, in practical applications,

Nous Research announced improvements to token streaming functionality for the Hermes Agent on Telegram, enhancing the smoothness and performance of real-time token generation. This update likely addre

The agent development lifecycle has been manual for too long. We’re building a future where it runs continuously, without manual triggers. Where well-understood issue types resolve without human revie

The Quarq agent is constructed using LangGraph, a framework that simplifies the development of complex memory systems. Quarq has achieved a top ranking on the LongMemEval benchmark, demonstrating the

arXiv:2606.01498v1 Announce Type: cross Abstract: Time series data inform critical decisions across many real-world domains. While large language model (LLM) agents can analyze data through natural la

arXiv:2606.02304v1 Announce Type: new Abstract: LLM-based agents can solve multi-step interactive tasks by combining reasoning with environment feedback, yet each episode starts from the same fixed co

Workday Inc. today announced new capabilities aimed at providing developers new ways to build on top of its platform using their own tools. During DevCon 2026, the company’s annual developer conferenc

all agents in the future are going to need to write and execute code LangSmith Sandboxes are GA - try them out today https://docs.langchain.com/langsmith/sandboxes .@MukilLoganathan’s Interrupt keynot

Demo2 showcases Qwen's multimodal interactive hybrid agent capabilities, likely demonstrating the integration of multiple data types (text, image, audio, video) with interactive features and hybrid pr

Demo3 showcases Qwen's browser agent capabilities, likely demonstrating an AI system's ability to autonomously interact with web browsers to perform tasks such as navigation, form filling, or informat

arXiv:2605.30915v1 Announce Type: new Abstract: Real-world images rarely suffer from a single degradation, and the order in which degradations are removed substantially affects the final restoration q

LangSmith's APAC instance now supports Fleet computer use, enabling Fleet agents to access virtual computers for enhanced functionality. This feature allows users in the Asia-Pacific region to leverag

arXiv:2605.31042v1 Announce Type: cross Abstract: LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and wr

In @latentspacepod podcast, I shared my view on video generation, world models, LLMs, agents, continual learning and where the next frontier is. 1. Video models get most of their intelligence from lan

arXiv:2605.31278v1 Announce Type: new Abstract: Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotati

Introducing Search as Code, our new search architecture for AI agents. It writes Python that calls our search stack directly, instead of looping through function calls one at a time. Available in the

arXiv:2605.30677v1 Announce Type: cross Abstract: Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source code of executable binary files. This r

arXiv:2605.31005v1 Announce Type: new Abstract: We present a differentiable optimization framework for multi-agent coordination. An input is decomposed into overlapping local views, each processed by

arXiv:2605.30738v1 Announce Type: new Abstract: Generalization across agentic tool-calling environments remains a central challenge for reliable agentic reasoning systems. Although large language mode

arXiv:2605.30711v1 Announce Type: cross Abstract: Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has foc

arXiv:2605.31593v1 Announce Type: cross Abstract: Language models can find thousands of severe software vulnerabilities, and agents are increasingly being misused for cyberattacks. To avoid detection,

LangSmith Engine is a tool designed to automatically diagnose and resolve agent failures, eliminating the need for manual troubleshooting and triage. The feature appears to leverage automated analysis

A practical comparison of production AI evaluation harnesses, including what to look for across instrumentation, evaluators, online evals, CI gates, and agent workflows. The post The best eval harness

arXiv:2605.29801v1 Announce Type: new Abstract: Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhi

arXiv:2605.29225v1 Announce Type: new Abstract: Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, lea