aiqbenchInformații despre AI & calcul cuantic

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchProduse AI

LangChain compares seven browser toolsets for its Deep Agents, selects Stagehand, and tunes it using LangSmith traces and evals. The useful takeaway for agent builders is that tool design, not only the underlying model, shapes how well a browser agent performs. Long task sequences (26 model turns on average for one WebVoyager task) and bloated page content are the core problems, and the article's claims rest on the authors' own benchmarks rather than independent testing.

Surse care acoperăLangChain Blog, Latent Space, arXiv, Google

How We Optimized Browser Use for Deep Agents

LangChain Blog3 noiembrie 20268 min de cititArticolul și perspectiva sunt în engleză.

We compared seven browser toolsets for Deep Agents, picked Stagehand from Browserbase, and tuned it with LangSmith traces and evals. Here's what we learned.

Browser agents can now take on multi-step work that's painful and time-consuming for people. Personal agents like Instinct and Meta's Muse plan cross-country road trips, cancel unused subscriptions, and list cars for sale, all on sites with no public APIs. DataDome saw agentic browser requests jump 4.7x in September alone. Browser use helps in two places: actions an API can't cover, like using a website the agent wasn't set up for, and end-to-end testing of the web apps coding agents build. Either way, the agent needs two things: Tools to drive the browser: open pages, read them, and act on them. Most toolsets control the browser over the Chrome DevTools Protocol (CDP), the protocol that lets tools inspect and control Chrome. A browser to drive, either local or hosted. Managed Deep Agents lets you build and deploy agents in LangSmith without running any infrastructure, and it can run the browser for your agent too (more in our launch post). A hosted browser provider like…

Extras afișat conform termenilor RSS ai publicației · 164 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe LangChain Blog ↗Întreabă despre acest articol

Subiecte conexe

Siguranță AI

Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming

arXiv · 6 iun. 2026