Search “Agents”

Artificial Analysis releases Coding Agent Index v2.0

On October 23, 2026, Artificial Analysis released Coding Agent Index v2.0, replacing DeepSWE with Cognition's FrontierCode v1.1 and tightening the repository question-answering scoring; the leaderboard evaluates model-plus-harness combinations. Reports that day showed Claude Code paired with Claude Opus 5.5 (max) topping the list with 61.7 points, Claude Code paired with Sonnet 5.5 second with 59.3 points, Muse Code paired with Muse Wonder Full at 58.9 points, and the first OpenAI combination, Codex paired with GPT-6 Astra, at 54.7 points. Regarding comparisons between the old and new leaderboards, earlier reports said the average score of 21 configurations fell from 58.8% to 57.1%; later reports said the mean for the same batch of 21 configurations dropped from 54.8 to 47.4, with 20 declining, and stated that the main reason was FrontierCode's mean of about 45.1%, far below DeepSWE's 65.6%.

Artificial Analysis releases Coding Agent Index v2.0

On October 23, 2026, Artificial Analysis released Coding Agent Index v2.0, replacing DeepSWE with Cognition's FrontierCode v1.1 and tightening the repository question-answering scoring; the leaderboard evaluates model-plus-harness combinations. Reports that day showed Claude Code paired with Claude Opus 5.5 (max) topping the list with 61.7 points, Claude Code paired with Sonnet 5.5 second with 59.3 points, Muse Code paired with Muse Wonder Full at 58.9 points, and the first OpenAI combination, Codex paired with GPT-6 Astra, at 54.7 points. Regarding comparisons between the old and new leaderboards, earlier reports said the average score of 21 configurations fell from 58.8% to 57.1%; later reports said the mean for the same batch of 21 configurations dropped from 54.8 to 47.4, with 20 declining, and stated that the main reason was FrontierCode's mean of about 45.1%, far below DeepSWE's 65.6%.

View story:Artificial Analysis releases Coding Agent Index v2.0

Aerial offers Agent-based automatic deployment to replace the TV's default launcher

Aerial is a tool that can replace the default launcher on Chinese smart TVs without root, and its deployment is completed automatically with the help of an Agent. According to an October 22, 2026 report by Huxiu, users connect the TV and computer to the same WiFi, enable ADB and find the TV's IP address, then copy the prompt from the Aerial official website and hand it to an Agent such as Doubao or WorkBuddy to execute; they only need to allow USB debugging in the pop-up on the TV, and the whole process takes about five minutes. The tool uses a "launcher guard" to cover the original launcher when it is woken up, and leverages Android notification listening to revive within 0.5 seconds after standby cleanup, so home-screen ads disappear, but boot ads still cannot be blocked. The report says that everything from the code and APK to the official website was produced through AI Vibe Coding; it gained more than 200 stars on GitHub within one day of launch, and subsequently added features such as icon hiding and adding signal input sources to the home page, and was adapted to multiple TV models.

Aerial offers automatic Agent deployment to replace the TV's default desktop

Aerial is a tool that can replace the default launcher on Chinese smart TVs without root, and its deployment is completed automatically with the help of an Agent. According to an October 22, 2026 report by Huxiu, users connect the TV and computer to the same WiFi, enable ADB and find the TV's IP address, then copy the prompt from the Aerial official website and hand it to an Agent such as Doubao or WorkBuddy to execute; they only need to allow USB debugging in the pop-up on the TV, and the whole process takes about five minutes. The tool uses a "launcher guard" to cover the original launcher when it is woken up, and leverages Android notification listening to revive within 0.5 seconds after standby cleanup, so home-screen ads disappear, but boot ads still cannot be blocked. The report says that everything from the code and APK to the official website was produced through AI Vibe Coding; it gained more than 200 stars on GitHub within one day of launch, and subsequently added features such as icon hiding and adding signal input sources to the home page, and was adapted to multiple TV models.

View story:Aerial offers Agent-based automatic deployment to replace the TV's default launcher

Shopify shares how Sidekick uses a post-trained open-source model as the GraphQL sub-agent

On October 21, 2026, the Shopify engineering team, in a talk at NVIDIA GTC Berlin 2026, shared the model division-of-labor plan for its e-commerce assistant Sidekick: a frontier model handles conversation planning, while a self-deployed open-source model handles the GraphQL sub-agent. The team chose the MoE model Nemotron 3.5 Lightning, with 30 billion total parameters and 3 billion parameters activated per token; after 6 rounds of post-training and 61,000 repair samples, the review score rose from 37.7 out of the box to 74.5, slightly above the frontier model's 73. On GraphQL tasks, the median response was 0.87 seconds, versus 6.50 seconds for the frontier model API, at roughly 90% lower cost. Currently this talk is a single-source report, with no follow-up developments yet.

English translation is being prepared.

On October 21, 2026, the Shopify engineering team, in a talk at NVIDIA GTC Berlin 2026, shared the model division-of-labor plan for its e-commerce assistant Sidekick: a frontier model handles conversation planning, while a self-deployed open-source model handles the GraphQL sub-agent. The team chose the MoE model Nemotron 3.5 Lightning, with 30 billion total parameters and 3 billion parameters activated per token; after 6 rounds of post-training and 61,000 repair samples, the review score rose from 37.7 out of the box to 74.5, slightly above the frontier model's 73. On GraphQL tasks, the median response was 0.87 seconds, versus 6.50 seconds for the frontier model API, at roughly 90% lower cost. Currently this talk is a single-source report, with no follow-up developments yet.

View story:Shopify shares how Sidekick uses a post-trained open-source model as the GraphQL sub-agent

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.

Meta updated its commercial terms, removing language that had been interpreted as allowing it to scrape website content to train AI. Neiman Lab and Cornell University law professor James Grimmelmann previously argued that the clause was intended to let Meta use scraped content for free to train AI, and could bypass blocking instructions in robots.txt. Meta Vice President of Communications Andy Stone and spokesperson Daniel Roberts had responded that Meta's use of web crawlers had not changed, and this terms update directly removed the disputed language. Other reports said that when Meta updated its business services terms, it had stated it had the right to use content from business account domains, web pages or URLs to train AI models, and deleted that language after controversy; Meta said the update was merely a consolidation of existing advertising terms, not an expansion of crawler behavior, and that the revised terms limit crawlers and data collection to advertising and business products only, while site owners can still control crawler permissions via robots.txt.

View story:Meta updates its commercial terms, removing language that could have allowed scraping of news website content

Arena announces DeepSeek-V4.1-Flash-1017 tops the Agent Arena open-source leaderboard

On October 17, 2026, DeepSeek released DeepSeek-V4.1-Flash-1017, which the company says delivers stronger benchmark performance, faster task completion, and shorter outputs, achieving a Pareto improvement in performance and cost; it is now available on the official website, App, and API, and the model also launched on OpenRouter the same day. The company also announced that the Search and Fetch APIs are open to everyone, priced at $0.75 per 1,000 calls per endpoint, with calls made through server-side tools in DeepSeek Harness, Claude Code, and Codex temporarily free, and billing starting at 16:00 UTC on October 31, 2026. On October 17, Thomas Wolf commented that DeepSeek called this a "minor update," yet Terminal-Bench 4.0 rose from 31.2 to 42.3. On October 19, Arena announced that the model, with a score of 1670, became the highest-ranked open-source model on Code Arena: WebDev. On October 20, OpenCode updated it to version 1017 in Go and Free; Unsloth released a GGUF that can run locally, with the 1-bit quantized version retaining about 88.2% accuracy and shrinking in size from 508GB to 250GB; Arena then announced that it topped the Agent Arena open-source model leaderboard.

View story:DeepSeek releases DeepSeek-V4.1-Flash-1017

The author announced that the practical experience had been compiled into "Eight Lectures on Agent Engineering in Practice"

On October 18, 2026, the author announced that the practical experience had been compiled into "Eight Lectures on Agent Engineering in Practice". On the same day, the Tencent Cloud Developer Community published an introduction to the series, describing how it focuses on upgrading prototypes that can call models and tools into systems that can complete business tasks, explain failures, control costs, and iterate continuously. The introduction states that the entire series runs through two fictional teaching cases—a case-filing assistant Agent and a postoperative follow-up Agent—covering eight topics: task contracts, reasoning and collaboration, context and memory, reliable tool execution, observability and replay, evaluation and calibration, security boundaries, and production operations; the text emphasizes that a model being able to suggest the next step does not mean the system can deliver business results, and that the example fields, budgets, and figures are all teaching calculations and do not constitute legal advice. Currently, only the introduction to the series has been published, and no factual evidence has yet been seen for the content of the subsequent lectures.

The author announces that practical experience has been compiled into "Eight Lessons on Agent Engineering in Practice"

On October 18, 2026, the author announced that the practical experience had been compiled into "Eight Lectures on Agent Engineering in Practice". On the same day, the Tencent Cloud Developer Community published an introduction to the series, describing how it focuses on upgrading prototypes that can call models and tools into systems that can complete business tasks, explain failures, control costs, and iterate continuously. The introduction states that the entire series runs through two fictional teaching cases—a case-filing assistant Agent and a postoperative follow-up Agent—covering eight topics: task contracts, reasoning and collaboration, context and memory, reliable tool execution, observability and replay, evaluation and calibration, security boundaries, and production operations; the text emphasizes that a model being able to suggest the next step does not mean the system can deliver business results, and that the example fields, budgets, and figures are all teaching calculations and do not constitute legal advice. Currently, only the introduction to the series has been published, and no factual evidence has yet been seen for the content of the subsequent lectures.

View story:The author announced that the practical experience had been compiled into "Eight Lectures on Agent Engineering in Practice"

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.

On October 13, 2026, Meta released the Muse Wonder series, comprising two models, Muse Wonder and Muse Wonder Full, which it called its most capable models to date, achieving SOTA on personal and professional agent tasks, covering professional domains such as law, finance, and health as well as frontier coding capabilities. Both models feature Active Memory and Active Focus, and were trained, evaluated, and released according to the Meta Superintelligence Scaling Framework. According to Artificial Analysis data, the two models scored 52 and 56 respectively on Intelligence Index v4.3 at maximum reasoning effort, higher than the 48 of Muse Spark 1.3 (max); Muse Wonder is already available on Meta's first-party API and Muse Code, while Muse Wonder Full is available only to Muse Code users. On the same day, Arena added the two models to Agent Arena testing, and Simon Willison released the llm-meta-ai 0.2 plugin supporting the new models. On October 14, Arena announced Muse W

View story:Meta launches Muse Wonder and Muse Wonder Full models

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.