Search: “agents”

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

arXiv:2605.29307v1 Announce Type: cross Abstract: Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and inf

This post from LangChain's Harrison Chase contrasts traditional manual methods of improving AI agents (tracing execution, identifying patterns, writing evaluations, and implementing fixes) with a more

arXiv:2605.29625v1 Announce Type: new Abstract: The topic of Co-creation, i.e., AI agents interacting with humans to generate outputs (e.g., art), has gained significant attention recently. However, m

arXiv:2605.30190v1 Announce Type: new Abstract: Diffusion-based planning has achieved strong results in single-agent offline reinforcement learning, yet scaling to many-agent systems remains intractab

arXiv:2605.29653v1 Announce Type: new Abstract: Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require sim

arXiv:2605.29224v1 Announce Type: cross Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating

arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new thr

arXiv:2605.29534v1 Announce Type: new Abstract: Recent advances in mobile GUI agents have shown strong potential for automating mobile tasks, but most effective systems still depend on large vision-la

Work management software company Asana Inc. today said it has completed the acquisition of StackAI Inc., a no-code platform for building artificial intelligence agents, in a deal that adds the ability

arXiv:2605.27864v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on p

arXiv:2605.27922v1 Announce Type: new Abstract: LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, perform

If you're building your own cloud agent like Devin or Ramp Inspect, there's lots of great details here on setting up VMs, computer use, memory, and more. Fun deep dive with the creator of OpenInspect

arXiv:2605.28721v1 Announce Type: new Abstract: Are LLM-based search agents genuinely searching, or using the web to verify what they already know? We study this question on BrowseComp with three diag

arXiv:2510.03534v5 Announce Type: replace-cross Abstract: We study the problem of long-term (multiple days) mapping of a river plume using multiple autonomous underwater vehicles (AUVs), focusing on t

Agentic artificial intelligence infrastructure startup Modiqo Inc. says it can assist companies in moving from experimental workflows to repeatable and production-ready systems after raising 3 million

arXiv:2605.27853v1 Announce Type: new Abstract: We present MolLingo, a multi-agent system that emulates the reasoning process of a chemist to automate molecular design. Existing LLM-based approaches e

arXiv:2605.28354v1 Announce Type: new Abstract: Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a

arXiv:2605.27760v1 Announce Type: new Abstract: Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However,

arXiv:2511.09572v2 Announce Type: replace Abstract: For agentic systems to use external tools to solve complex, long-horizon tasks, we need a large set of diverse and controllable tool-use environment

arXiv:2605.28588v1 Announce Type: cross Abstract: We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation

This episode of the Latent Space podcast features Walden Yan from Cognition and Cole Murray from OpenInspect discussing the emerging paradigm of asynchronous AI agents—autonomous systems that operate

arXiv:2605.27721v1 Announce Type: cross Abstract: Understanding what a user believes and intends is central to building effective agent assistants. This ability is often evaluated through Theory-of-Mi

arXiv:2605.27593v1 Announce Type: new Abstract: Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collus

arXiv:2605.28224v1 Announce Type: new Abstract: Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowle

Nous Research announced a live Discord event called the Hermes Agent Jam Session with 384 participants, where developers showcased ongoing projects and innovations. The event provided a venue for the

arXiv:2605.26178v1 Announce Type: cross Abstract: Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. Howeve

This post likely announces or discusses an open-source AI agent framework that incorporates memory and continual learning capabilities, enabling the system to retain information across interactions an

📹 How to manage context the right way with LangSmith Context Hub Context Hub gives your team and your agent a shared place to store, edit, version, and retrieve context from It can be used for skills,

LangSmith has introduced automated tools to streamline agent improvement, eliminating the manual workflow of reading execution traces, identifying patterns, writing evaluations, and implementing fixes

arXiv:2603.01131v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown promise in clinical diagnosis but remain limited by unreliable report generation, weak evidence ground

arXiv:2605.26691v1 Announce Type: new Abstract: Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume t

arXiv:2605.26870v1 Announce Type: cross Abstract: Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens wh

the future of Continual Learning will rely on building to systems to ingest, understand, & apply knowledge from Agent Traces at scale had a blast presenting LangSmith Engine with @bentannyhill to show

this is a fantastic example of a robust agentic memory system built on langgraph! there's 4 key parts 1. retrieval (rag) 2. storage, fragmented by memory type 3. reasoning* 4. learning (often called d

Nous Research announced an upcoming 'Hermes Agent Jam' event starting in 2 hours from the time of posting. The event likely involves developers and AI researchers collaborating on or demonstrating app

arXiv:2605.26144v1 Announce Type: cross Abstract: We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike

arXiv:2605.27141v1 Announce Type: new Abstract: Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such setti

We launched Context Hub as a way to manage skills, AGENTS.md files, and other context files an agent might need You can easily use it as a virtual filesystem in deepagents See this video for more info

arXiv:2601.04426v3 Announce Type: replace Abstract: Modern LLM agents increasingly rely on dynamic structured generation, such as tool calling and response protocols. Unlike traditional structured gen

arXiv:2605.25707v1 Announce Type: new Abstract: Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digita

arXiv:2510.10185v2 Announce Type: replace-cross Abstract: Large language models are increasingly being assembled into medical multi-agent systems that emulate multidisciplinary consultation through sp

arXiv:2602.01086v2 Announce Type: replace Abstract: Background: As of 2026, Large Language Models (LLMs) demonstrate expert-level medical knowledge. However, deploying them as autonomous 'Clinical Age