Agent Frameworks

LangChain shares how it built internal agents for marketing, sales, and engineering, distilling its experience into five core primitives: living in Slack, scoped identity that mixes on-behalf-of and fixed credentials, global and user-level memory, sandboxed code execution, and a large share of runs triggered by schedules or events rather than people.

LangChain explains how the Deep Agents harness handles retrieval for limited-context agents by searching before reading, offloading oversized tool results, and delegating filtering to subagents.

Many teams build a multi-agent AI prototype in days but hit a wall in production. This post defines five production challenges (orchestration, per-agent model selection, reliable operation, secure code execution, and monitoring) and shows how Deep Insight, an open source multi-agent system on AWS, solves each.

How Numan built Nu, an AI health coach, on LangGraph and LangSmith with per-category evals, simulated conversations, and safety gates on a regulatory line.

NVIDIA has released the full Run:ai GPU orchestration platform as open source under Apache 2.0. The release includes KAI Scheduler, CUDA 13.4 GPU fractioning, quota management, and a local Kind dev environment. The post NVIDIA Open Sources Run:ai Under Apache 2.0 for Kubernetes GPU Orchestration appeared first on MarkTechPost.

arXiv:2610.20615v1 Announce Type: new Abstract: Adaptive optimization workflows in machine learning, federated learning, quantum machine learning, and hybrid classical quantum systems often embed controller logic directly inside task specific training scripts. This coupling limits reuse, reproducibility, safety validation, and fair comparison across execution environments. This paper presents DeepUnfolding Agent, a schema-driven FastAPI platform that exposes deep unfolded adaptive control as an external software service. External executors register a strategy schema, submit round-level diagnostic variables, receive schema-bounded control actions, execute one optimization round, and return feedback for controller update. The framework separates controller intelligence from domain specific…

arXiv:2610.20780v1 Announce Type: new Abstract: In LLM-based multi-agent systems (MAS), a local mistake can propagate as other agents build on it, turning a correctable error into a failed task. Diagnosing completed runs or repeatedly re-executing them to search for corrections does not provide a learned policy for intervening while execution is still in progress. We present Agent Runtime Inspection and Amendment (ARIA), a framework for learning when and how to repair ongoing multi-agent executions. Our key intuition is to turn execution-verified repairs into reusable supervision, moving repair search into data construction and training so that a learned model can intervene at runtime without repeatedly testing alternatives. First, we collect over 24{,}000 successful and failed trajectori…

What we shipped at Interrupt NYC and London: LangSmith AI Search, Engine v2, Trajectories, Custom Apps, Fine-Tuning, and Managed Deep Agents v0.9.

Where to start with agent evals, offline vs online evals, evaluator types, LLM judges, benchmarks with Harbor, multi-turn evals, and keeping costs down.

Long-running agents degrade as context piles up. Learn how offloading, summarization, skills, subagents, and memory keep your agent's context window focused.

Learn how Orange Business used LangChain and LangSmith to build Live Intelligence, a governed AI platform for agents, evals, observability, and production scale.

Stale code samples are a docs problem nobody prioritizes. Here's how we used the Deep Agents CLI to automate migrating inline code into testable, CI-ready examples

Harness engineering improved LangChain's coding agent from Top 30 to Top 5 on Terminal Bench using self-verification, tracing, and context optimization.

Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way to deploy a model agnostic, open source agent harness in a production ready way.

AI Search in LangSmith is a new way to query traces using natural language. Describe the behavior you're looking for, and LangSmith returns the traces where it happened.

Use ScaleDown's constrained decoding models with LangChain and Deep Agents to summarize history, compress tool results, and extract data faster and cheaper.

arXiv:2610.12593v1 Announce Type: new Abstract: The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable and verifiable trajectories, but also interactions that provide learning value for the current task agent. Existing methods increasingly incorporate environment feedback, data validation, or learner failures, but still face a feedback-to-decision gap: observed weaknesses do not directly specify how future synthesis should change, or whether they can be represented by the current synthesis space. To address this gap, we propose EvoSyn, a learning-feedback-driven multi-agent framework that organizes synthesis around a revisable state specifying what interaction factors…

Managed Deep Agents includes a new API for managing reactions for your distributed agents, and a system to dynamically assign emoji responses with your instrument of choice. Learn more.

arXiv:2610.10812v1 Announce Type: new Abstract: Small language models (SLMs) have been increasingly adopted for onboard robot operation because they enable intelligent decision-making. However, existing approaches are mainly distillation-oriented and rely on enumerating representative task-solution pairs. This makes dataset construction difficult and limits generalization to diverse robot tasks whose possible forms grow rapidly. This paper proposes Skill-SLM, a framework that reformulates SLM-driven robot operation as a task-decomposition and skill-composition problem. Given a natural language task instruction, Skill-SLM decomposes the task into subtasks, selects appropriate skills from the skill library, and orchestrates the selected skills into executable robot operations. First, to sup…

Discover how Snyk transformed an internal support agent into Snyk Assist, a customer-facing AI feature powered by LangChain, LangGraph, and LangSmith.

Build an agent that pays for real purchases. Restock runs in Slack on Managed Deep Agents and pays with Stripe's Link over the Machine Payments Protocol.

arXiv:2610.08933v1 Announce Type: new Abstract: Deep-space crews cannot rely on real-time ground support for urgent off-nominal events. Initial alerts may underdetermine cause, while discriminating evidence may reside in crew observations or at locations that are unsafe, costly, or unavailable for crew inspection. We present an evidence-driven architecture for human-agent-robot teaming in Earth-independent anomaly triage. Agentic AI is treated as a stateful coordinator over bounded, inspectable services rather than as a fully autonomous vehicle controller. A triage state manager maintains hypotheses, evidence provenance, uncertainty, operational context, and tool status; a crew-facing embodied agent elicits observations and explains assessment changes; and a mobile robot acquires targeted…

Deep Agents now lets you bind tools to skills, pin skills at runtime, and reload skills mid-thread, so agents with expansive skill repositories stay context-efficient and effective.

LangChain just released new capabilities in Managed Deep Agents. Agents can now schedule follow-ups, reconfigure themselves on every run, and react to Slack messages.

arXiv:2610.06971v1 Announce Type: new Abstract: Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications. Present observability tools only raise alerts but for human engineers, resulting in a high Mean Time to Repair (MTTR) and operational fatigue. In this paper we propose AegisFlow (Agentic Engine for Intelligent Self-healing and Graph-driven Operations for Workload remediation), a novel agentic framework that closes the loop between detection and resolution. AegisFlow uses a Watchdog agent to collect runtime telemetry and has a Repair agent to automatically create, test and deploy code patches based on Large Language Models (LLMs). The framework presents the non-intrusive execution model called Par…

Build a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions that single-shot retrieval answers poorly. Run the same query through both paths, read the trace events, and compare what each retrieval path costs.

How we built a model router into Open SWE's harness that cut median cost per coding task by 64% with no measurable drop in quality, and how to build your own.

arXiv:2609.35809v1 Announce Type: new Abstract: The rapid advancement of generative AI raises concerns about the misuse of Multimodal LLMs (MLLMs) for large-scale disinformation campaigns on social media. Despite existing research on textual disinformation, a fundamental question remains unanswered: can MLLMs be exploited to fabricate realistic multimodal fake news, and can they reliably detect it? We introduce a multi-agent framework in which a story agent, an image agent, and a critic agent collaborate to produce fake social media posts that plausibly counter true news. We apply the framework to generate over 9,000 paired multimodal news posts across science, health, and entertainment domains, and benchmark 16 open- and closed-source MLLMs for automated detection. We find that most mode…

Today, I’m talking with Mike Cannon-Brookes, who is cofounder and CEO of Atlassian. Atlassian is one of those companies that every other company runs on — it makes important platform tools like Jira and Trello that allow people to organize and manage big teams, create shared databases of company information, and generally allow work to happen. As you’ll hear Mike say, all of Atlassian’s products are actually different expressions of a single core platform, which really shapes how Atlassian itself is structured and how those products are built. All of this means Atlassian is also right in the middle of the way AI is changing how all these companies work — AI tools might be able to look at all the different tools and systems you have and just read them for you, making a big migration to Atl…

arXiv:2609.30450v1 Announce Type: new Abstract: Optical lens design is a complex, non-convex optimization challenge that relies heavily on human experience and intuition. Existing optimized-based automatic lens design methods struggle to navigate this vast parameter space without meticulous manual tuning. In this paper, we present LensDesigner, an autonomous agent framework that mirrors the problem-solving workflow of expert opticians. To overcome the initial cold start problem, we construct LensLib100K, an extensive optical lens library, and employ Optics-Aware Retrieval to supply physically valid structural seeds. Within an interactive physical simulation environment, the agent executes macroscopic orchestration while receiving immediate optical feedback. Furthermore, we introduce a con…

arXiv:2609.30294v1 Announce Type: new Abstract: Scientific presentations are more than summaries of research papers. They need to present the work in a coherent sequence, explain the main ideas clearly, and help the audience follow the presentation. We present SlideLab, a training-free multi-agent framework for generating scientific presentations from research papers. SlideLab first plans the presentation narrative, then builds and iteratively refines a shared slide deck using agents for content planning, visual generation, layout refinement, and grounding verification. In a blind human preference study, SlideLab was preferred over both open-source and commercial systems on 77% of papers while using roughly 4 times fewer inference tokens than the strongest open-source baseline. We also in…

See how LangGraph orchestrates Jev, TypeSafe AI's decision model, to build faster, cheaper production agents.

NarrateAI delivers production-ready LLM quality assurance on Amazon Bedrock. This post details five techniques—adaptive pipeline orchestration, cross-account multi-model failover, real-time streaming evaluation, composite evaluation, and data accuracy verification—that reach about 99% numerical accuracy while streaming responses in real time.

LangChain announced new updates to LangSmith. Updates include Engine v2 with red teaming and automatic testing, a new version of Managed Deep Agents, trajectories and more.

arXiv:2609.28557v1 Announce Type: new Abstract: DNA sequencing pipelines, spanning quality control, alignment, variant calling, and annotation, are now reliably executed by workflow management systems that orchestrate established bioinformatics tools at scale. What remains manual is the decision layer surrounding that execution: selecting quality thresholds appropriate to a sample and platform, adjudicating borderline variant calls, diagnosing anomalies, and determining which findings warrant expert review. These decisions are repetitive, judgment-intensive, inconsistent across operators, and frequently undocumented. This paper introduces BaseCamp, a novel agentic AI framework for automating the decision layer of DNA sequencing pipelines. The framework decomposes the pipeline into six spe…

LangSmith Custom Apps lets you build the interface you want with your LangSmith data, publish it into your workspace, and skip the hosting, auth, and permissions work. Learn more.

LangChain introduces LangSmith Fine-Tuning and SmithTune, a CLI built for post-training models. Train specialized models without building data pipelines by hand.

Trajectories in LangSmith provide a conversational view of an agent session. Trajectories make trace data easy to navigate and speed up debugging for long-running agents.

LangSmith Engine now includes Red Teaming to proactively detect agent issues and automated agent testing. Learn more about the Engine v2 release.

Managed Deep Agents is the simplest way to build, deploy, and run agents in production. The 0.8 release adds support for user-owned credentials, user-level memory, HTTP channels, file transfer in Slack and a pre-built tool for web search.

arXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the \textit{agent loop}, where the LLM is placed in an environment exposing a set of tools, and the LLM has full control over the workflow by alternating between tool calls and observing their output. However, certain workflows currently require additional engineering beyond the agent loop itself, such as memory systems and self-improving systems. We built an LLM agent framework, JAZ, to explore the extent to which a minimal harness that is little more than the agent loop itself can accomplish tasks these specialized systems are built for. JAZ exposes a single LLM-based primitive invoke and provides a set of built-in hooks that allow the programmer to apply constraints and monitoring. Generalizin…

Learn how to build a conversational video intelligence solution on AWS using an agentic architecture. A single Strands Agents SDK agent orchestrates Amazon Bedrock, Amazon Rekognition, and Amazon Transcribe at runtime, deciding which service to call so you can ask natural language questions about your videos and get answers in seconds.

See how LangSmith helps healthcare AI teams turn clinical review into reusable evaluators, datasets, and release gates for safer AI in production.

Use Jev as a judge for LangSmith evals to evaluate agent traces with faster, cheaper structured feedback across production runs, datasets, and regression tests.

Python Workers allow developers to run Python web frameworks and AI orchestration libraries natively in the Cloudflare Workers runtime. You can seamlessly integrate with Cloudflare's ecosystem including D1, R2, and Workers AI without writing any JavaScript glue code.

We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation.

Migrate a multi-model healthcare AI agent from self-managed Amazon ECS with AWS Fargate to Amazon Bedrock AgentCore runtime, preserving triple-model orchestration and vector-enhanced knowledge retrieval while reducing infrastructure management. The framework-agnostic pattern applies across healthcare, financial services, and manufacturing.

Building an AI prototype is easy, but operating autonomous agents at scale requires production-grade tooling. Salesforce Agentforce bridges the gap from "vibe coding" to enterprise reliability by combining synthetic stress-testing, real-time optimization, dynamic agentic UIs, and deterministic guardrails—as proven by Southwest Airlines' 7x ROI. The post Salesforce Agentforce: Bridging the Enterprise AI Gap from ‘Vibe Coding’ to Battle-Tested Orchestration appeared first on MarkTechPost.

arXiv:2609.19391v1 Announce Type: new Abstract: LLM coding agents now generate complex programs at a scale that makes thorough human review increasingly difficult, raising the risk of safety and security failures. Common approaches, including fuzz testing, static analysis, and LLM-as-a-Verifier, can detect many failures but struggle to cover all possible edge cases. Formal verification addresses this by providing machine-checkable guarantees over specified properties, but traditionally demands substantial manual specification and proof engineering. We introduce a unified multi-agent framework, MAGS, that generates executable programs with formal safety guarantees, using Dafny as a verification-aware intermediate representation where safety properties can be mechanically checked. MAGS form…

Open Source Agent Architecture LangChain Building a Harness with Jev September 17, 2026 5 min Go back to blog Create agents Agents run in a loop: an LLM decides what to do, a tool executes, a model evaluates the results…