AI · Official
How LangChain Tuned Its Browser Tool to Make AI Agents Work Better on the Web
LangChain blog ·

At a glance
The LangChain team chose a browser tool that lets AI agents operate websites directly, then improved it by reviewing real records of agent work. After comparing several tools, they picked Stagehand and checked the effect of each change with tests.
Key points
- Web tasks involve many steps, and in some cases the model responded an average of 26 times for a single task.
- Web pages contain a lot of content, but only a small part is actually needed, so the tool must handle information efficiently.
- The team read agent work records to find wasted steps, improved the tool, and then checked it with several benchmarks.
- By requiring answers in a structured format, format mistakes in answers were kept out of the browsing evaluation.
Why it matters
More AI agents are carrying out multi-step web tasks for people, so how cheaply and accurately they do this work matters.
Original source
How We Optimized Browser Use for Deep Agents
LangChain blog · Nov 6, 22:12 KST
Read on LangChain blog ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to LangChain blog.
More from this field
- OpenAI Opens ChatGPT Space to Plus Users for Pages, Slides, and Team Sharing
OpenAI opened ChatGPT Space to Plus users on the 20th, local time. Space works as a new home for pages, slides, images, files, and uploads. Users can write pages with ChatGPT, add interactive charts, turn ideas into slides, and invite others to edit together.
AI 매터스 · Nov 21, 11:26 KST - Anthropic Researcher Claims Claude Helped Prove Riemann Hypothesis, Experts Await Review
Wes Roth covers a claim by Anthropic researcher Levent Alpöge that he proved the Riemann Hypothesis with help from the AI model Claude. He looks at the huge Lean formal proof, reactions from mathematicians and AI safety researchers, and what this could mean for AI and math.
Wes Roth · Nov 21, 11:24 KST - Korea Orders Overhaul of National Exams and Hiring to Stop AI Cheating
President Lee Jae-myung ordered a full overhaul of national exams and private company hiring to stop people from cheating with AI, from the college entrance exam to job exams. A government-wide task force and a Blue House task force were launched at the same time.
서울경제 · Nov 21, 10:35 KST - AWS Quick Adds Chat-Built Workflows and Multi-Agent Orchestration
Amazon Web Services released a large AWS Quick update on November 20, 2026. Users can now build business workflows by chatting, and the update adds orchestration that combines results from several specialist agents.
Unite.AI · Nov 21, 10:20 KST