Search: “agents”

Very cool paper from Microsoft. The idea is to train agents on replayed teacher trajectories instead of live environment rollouts. On-policy distillation for agentic tasks is expensive because every u

This incident is deeply concerning. AI agents are willing to cheat and deceive to achieve misaligned and unintended goals, behaviours which have been demonstrated in controlled tests for months. Now,

For coding agents, trustworthiness has to be tested in the harness where the model actually writes code. In one surveillance scenario, Kimi K2.7 complied with the request in 8/8 samples. SWE-1.7 refus

DSGym is a comprehensive framework designed to evaluate and train AI agents for data science tasks, providing a structured environment for benchmarking agent performance across various data science wo

Introducing Computer in WorkPods. Computer lets your agents use a browser. Every task that lives on the web, behind a login, a form, a button, now runs inside the same session you're already watching.

OpenWiki is the easiest way to document your codebase, built specifically for agents to consume. OpenWiki can generate repo docs, automatically update them as your codebase evolves, and do Q&A over yo

Recursive Language Model (RLM) workflows are now available as a feature in Deep Agents, allowing AI systems to iteratively call language models within multi-step processes. This capability enables mor

Building voice agents can come with tradeoffs. 💬 Better convos w/ speech to speech models Vs 🥪 More reliable harnesses w/ sandwich architecture How to build a voice research agent with both: ✅ Gemini

Giving agents the ability to write code makes them dramatically more capable. It also makes security a lot harder. At LangChain, we have spent a lot of time this year figuring out how to do both. http

Sonnet 5 is here! This is going to support better long-running agents. Previous Sonnet models were unreliable, so it's great to see the improved version that can complete agentic tasks more reliably.

This guide demonstrates how to build a voice agent using Vercel's AI Gateway, enabling real-time voice interactions with AI models. It covers the technical setup and implementation steps needed to cre

Deep Agents supports sandboxes from any provider; with first-class support for E2B, Daytona, LangSmith, Modal, Vercel, Runloop, AgentCore, and BYOS (bring-your-own-sandbox implementation) support http

Fleet agents can be shared in channels where your company is already doing work. Slack, Teams, etc Video from Caspar showing how to bring them into Slack! For agents to spread through a company they h

In a real conversation, deciding when to speak takes about as much brainpower as deciding what to say. Voice agents haven't been built that way. @SierraPlatform's unlock was parallelizing thinking, li

The AI SDK Harness API now supports @OpenCode and @LangChain Deep Agents through a single unified interface. Use 𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝 to run any supported runtime without changing your app code. https://verce

GLM 5.2 is already top 10 on OpenRouter this week, sitting right next to Opus 4.8. it's also been really strong in Deep Agents across long-horizon coding, big context, tool use, and verifying work bef

🧠Self-Harness: Harnesses that improve themselves New paper on agents shaping their own harnesses to improve over time. Not from LangChain, but builds on top of DeepAgents! Three key steps: 1/ Weakness

One of the better agentic AI courses I've seen Nearly 10 hours of great content. Covers LangChain, LangGraph, RAG, deepagents, guardrails, and more Any other good Lang* resources out there for folks w

in arxiv paper #2, i tackle the last topic from paper #1: @activegraphai as an architectural affordance for self-improving agents 'Regimes: An Auditable, Held-Out Gated Improvement Loop Demonstrated o

Research indicates that autonomous agents with greater operational autonomy, particularly in computer-based tasks, demonstrate improved performance quality and user satisfaction outcomes. The study su

We got into Y Combinator! Agnost AI (YC S26) is the infra for self-improving AI agents. We plug into conversational AI companies, find what's broken, and ship the fix as a PR. You just merge. DM if th

We published new research with Harvard on the shift from chat interfaces to autonomous agents like Computer. Over 3 months, findings show workers using Computer finish tasks in 87% less time at 94% lo

Witan Labs is developing a headless Office stack designed specifically for AI agents, combining productivity tools and capabilities without a traditional user interface. This post appears to be a week

On the latest episode of Max Agency, @hwchase17 sat down with @nlarusstone, Head of AI at @benchling for a conversation on building agents for scientific work. ⏯️ YouTube: https://www.youtube.com/watc

Prompting agents to 'do better' is unreliable 🙅 Giving them a rubric, a grader, and a correction loop is much closer to how you get your agent do what you want! Similar to /goal in Claude Code or othe

.@Rippling AI runs on Deep Agents and LangSmith. Here’s how they shipped to millions of users in 6 months. https://www.langchain.com/blog/how-rippling-went-ai-native-across-every-product-in-6-months-w

i had to pack away my coding agents on monday cuz I knew I’d stay up too late if I played w activegraph during the week (yay, it’s Friday!) gautham kept playing with it and just showed me a custom UI

Great conversation on the Max Agency podcast with @cogent_security Co-Founder + CTO Geng Sng on building agents for autonomous cyber defense. Check out the full episode: ⏯️ YouTube: https://youtu.be/D

as agents run for longer and with more context, there's a lot of tricky things you have to consider for deployment! super excited to dive into deploying Deep Agents for this Boston tech week meetup! .

the core concept is a graph that represents everything about the agents knowledge, history, behaviors, capabilities graph is made of events behaviors react to graph changes relationships can carry beh

working on some hex dashboards -- this is a bummer! if you use langchain/deepagents as your agent harness, you can swap models with fallback middleware when your first choice provider is down https://

Curious finding while creating evals and benchmarks for long-horizon (100+ turn) agents While it’s generally thought that a direct swap to open source models can bring immediate cost savings, that’s n

@LangChain’s Interrupt 2026 conference was a blast!! such a pleasure to with @VictorMoreira16 about deep agents! ICYMI: we just dropped v0.6, which is focused on performance at the model, harness, and

if you're already thinking about hacking around on agents this weekend, why not play around with @videodb_io api and potentially win a prize? videodb is an API for turning streaming video into text in

Introducing LangSmith LLM Gateway: The runtime governance layer for your agents. 💸 Enforce cost limits 🔒 Detect PII ✅ Act on violations …All without leaving LangSmith. Now in Private Beta https://www.

Not to mention 7 blog posts dropped today, including a new Deep Agents version with significant improvements… Especially excited about the Code Interpreter feature which is a sneaky powerful feature e

we just shipped delta channels in langgraph 1.2. as agents run longer and use more context, full-state checkpointing doesn't scale, but delta channel snapshots do. this new algorithm is now powering m

Dealing with quirks introduced by switching models doesn't have to be hard -- we recently introduced a 'harness profile' API in Deep Agents as a solution. Profiles adjust system prompts, tool descript

Replit announced the availability of Parallel Agents, a feature that allows developers to run multiple AI agents simultaneously on their platform. This capability enables more efficient and complex ta

'Tis the year of open source LLMs in agents! .@BraceSproul changed our org's internal model in Fleet from Sonnet 4.6 to Kimi K2.6 and I didn't even notice. Open models are already good enough for most

Anthropic just shipped sleep into agents. When you sleep, your hippocampus replays the day's neural sequences to the cortex during 150-220 Hz bursts called sharp-wave ripples. The replay runs about 20

As agents generate more code, review is becoming the bottleneck. You can write a PR in minutes, but understanding whether it's correct, safe, and ready to merge still takes longer than writing it. Dev

Finance Search supports questions that use live market data: prices, fundamentals, earnings, filings, and market context. Agents can run valuation lookups, earnings recaps, and market monitors without

🎉 @CBinsights AI 100 2026 is out and LlamaIndex made the list. We're proud to provide the leading document understanding API for AI agents. Congrats to all honorees in the AI Infrastructure category.

i'll be speaking in NYC this thursday on memory for agents! i'll be talking about filesystem backed memory, owning memory with an open harness, background memory consolidation, and more! https://luma.

A small, but very useful change! We added this based on our learnings while developing agents in Fleet, so you know it’s a useful addition new mode for LangChain's human in the loop middleware: respon