Evidence brief

OpenRouter uses BrowseComp to evaluate search configurations

OpenRouter releases a real-time leaderboard evaluating combinations of models, search engines, search methods, and budgets; results say increasing the search budget from 1 round to 25 rounds can nearly double BrowseComp scores, and model choice matters more than the search engine.

Published: 2026-08-13
Updated: 2026-08-13
Editorial: Frontline Lab

Source: OpenRouter：Announcements（RSS）
Source author: OpenRouter：Announcements（RSS）
Related topics: 1
Collected: 2026-08-13

Frontline Lab summary and source

Editorial summary

This brief preserves the original source so the summary and editorial context can be checked independently.

Source attributionOpenRouter：Announcements（RSS） · OpenRouter：Announcements（RSS）

Open the original source

Related published evidence

Relationships are derived from shared topics, entities, categories, tags, and community context; every result remains independently source-linked.

LangChain：Blog（RSS）2026-08-13

Agent workflows: LangChain explains what an AI agent is.

AI agents are systems that run autonomously in a large language model loop, completing complex tasks by repeatedly calling the model, observing results, and adjusting the next action. A workflow is a prearranged set of fixed steps. The two complement each other: workflows provide determinism, while agents provide flexibility. Understanding the difference is key to building reliable, production-ready autonomous systems.

Original source

OpenAI: official site updates (RSS · excluding enterprise/customer cases)2026-08-13

OpenAI: research: how companies use ChatGPT and Codex to deploy agentic AI

OpenAI research reveals how companies are adopting agentic AI, and how frontier companies are pulling ahead in AI applications. Companies are using ChatGPT and Codex to move AI from assistance to execution, while leading firms have already put agents into real business workflows.

Original source

GitHub Blog2026-08-13

OpenAI: how AutoGPT uses AGENTS.md and skill gating to manage AI-generated pull requests

AutoGPT maintainers found that AI agents do not proactively read documentation, so they put instructions in AGENTS.md and skill files next to the code directories. Through gating mechanisms such as mandatory PR templates, test plans, CI coverage thresholds, and CLA signatures, they turned agent-submitted PRs from “unusable” into “usable but not aligned with the roadmap.” Because CLA signing requires a browser and OAuth flow, it is used as a “human detector” to distinguish humans from agents.

Original source

X2026-08-13

STANFORD course covers self-correction and deep research agents

The post says STANFORD released a free course on building self-improving agents. The course focuses on self-correction and covers test-time compute, verifiers, Constitutional AI, RL, planning, memory, and tool execution.

Original source

X2026-08-12

Agent workflows: building a social media agent with Managed Deep Agents.

@hwchase17 reposted @caspar_br’s post, which said he made a YouTube tutorial on building a social media agent with Managed Deep Agents. The original post also said the agent scans “Hacker N…,” but the content is truncated.

Original source