AITOPAI热报
ProductsSelected

Managed Deep Agents 0.10 开启公测：新增浏览器操作与异步子智能体

官方账号LangChain@LangChainAI
Post
View the post
Why we picked it

LangChain 的 Managed Deep Agents 更新到 0.10 了，智能体现在能直接操作没 API 的网页，登录时用户手动接管，密码不会泄露给模型。

LangChain 发布 Managed Deep Agents 0.10 公开测试版。新版本为智能体加入浏览器能力，可以直接操作没有 API 的网页，需要登录时会把窗口交给用户，避免密码进入模型上下文。0.10 还支持异步子智能体，让长任务在后台运行的同时主智能体继续对话，并新增线程来源查看和停止运行等功能。

Original · LangChain

Managed Deep Agents 0.10: Now available in public beta 🌐 Browser use: Your agent can now work on websites with no API 💬 Async subagents: Run long tasks in the background while your agent keeps talking 🧵 Thread origins and stopping runs ...and so much more nathan drezner @ndrezn most of the web has no API, just pages built for people clicking through them so! we added a browser to Managed Deep Agents. and when a site wants a login, agents can hand over the window so passwords stay out of the model. all built in with every MDA x.com/i/article/2115… 🔗 View Quoted Tweet 💬 4 🔄 0 ❤️ 12 👀 1959 📊 5 ⚡

#LangChain#Managed Deep Agents#智能体#浏览器自动化#MCP/工具

Keep reading

Recent stories with the same tag or section
PapersBuildersMulti-sourceSelected23:07
MCP-Injector shows tool faults cut agent scores 60%

Scaling up model size does not buy robustness against broken tools, so engineering effort belongs in framework-level error handling and fault-injected evals rather than bigger models. Teams shipping MCP-based agents in production should test against MCP-Injector-style failure mixes and compare their agent stack choices, since the framework mattered more than the model. The fault calibration is derived from real open-source MCP repository issues, making the findings directly reusable for benchmark design.

#MCP-Injector#MCP#agents#gpt-oss
Event
DAIR.AI@dair_ai11 sourcesSource
How-toBuildersSelected03:52
LangChain's Harrison Chase Shares Agent Building Lessons on Twenty Minute VC

The model-plus-context-plus-harness decomposition gives teams a concrete decision framework for where to invest effort first, rather than defaulting to fine-tuning. Practitioners building or budgeting for agents get a tested sequence for cutting spend and a candid view that memory distillation is still the hardest unsolved piece. The claim that horizontal agents will call vertical agents also hints at where agent infrastructure investment is heading.

#LangChain#agents#coding assistants#open-source models
官方账号LangChain@LangChainAISource
How-toBuildersSelected03:52
LangChain: run agent evals through the same graph

Testing evals against the production agent graph removes the gap between what benchmarks measure and what users actually experience. Builders of conversational or multi-turn agents can reuse this pattern: simulate personas through the same entry point as live traffic, then trust the same scores in CI. It pairs well with LangSmith-style tracing workflows for regressions.

#LangChain#agents#evals#LLM personas
官方账号LangChain@LangChainAISource