Search “Search”

Tencent announces a brand-new upgrade of Yuanbao Search and opens it to developers

Tencent announces a brand-new upgrade of Yuanbao Search and opens it to developers. According to an October 21 report, Tencent is opening Yuanbao Search capabilities to external parties, offering three access methods: Skill, MCP, and API, with a limited-time free quota of 2,000 calls per month, and up to 6,000 calls per month via invitation codes in October and November. Yuanbao Search has built a hundred-billion-scale index, covering 13 vertical industries including finance, government affairs, and healthcare, and connecting 157 authoritative sources, with average daily calls reaching hundreds of millions, supporting more than 50 core businesses such as WorkBuddy and ima. A Zhidongxi hands-on test shows that a single API call takes an average of about 0.42 seconds. Another report the same day said Tencent Cloud announced on October 20 that Yuanbao Search is officially open to external parties, with services divided into Express, Standard, and Flagship editions, priced from 14 yuan per thousand calls, and the interface returns sorting information and data fields in JSON format.

View story:Tencent announces a brand-new upgrade of Yuanbao Search and opens it to developers

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.

Helion supports joint search of compiler controls and kernel configurations

Helion now supports incorporating compiler control parameters and kernel configurations into a single search. According to a PyTorch Blog article dated October 19, 2026, PyTorch Helion searches ptxas compiler control parameters through NVIDIA CompileIQ, jointly with the original kernel configuration search, further tapping performance headroom on about 27 kernels that have already been pre-tuned. CompileIQ packages tuning results as a portable Advanced Control File (ACF); Helion supports both specifying a fixed ACF and searching multiple ACFs together as one dimension of autotuning. These compiler controls have been exposed by ptxas since CUDA 13.3. There are currently no subsequent developments.

Trendos co-founder proposes criteria for judging AI search visibility

Trendos co-founder Gintare Rimolaityte proposes that whether a brand is mentioned in AI search depends on five key sources: its official website, PR, review platforms such as Trustpilot and G2, affiliates, and social media; content should answer questions directly in an FAQ style rather than stuffing keywords. Trendos is an AI search visibility platform that, by scraping LLM conversations at scale, helps brands monitor and optimize how they appear in AI search across ChatGPT, Gemini, Claude, Perplexity, and others. The above content comes from an interview report published on October 17, 2026; no subsequent developments have been seen so far.

Imperial College London Study Reveals Search-Augmented LLMs Cite Sources Without Reading Them

On October 16, 2026, three authors from the Department of Computing at Imperial College London published the paper "Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence," investigating why search-augmented LLMs frequently cite web pages they never actually opened. The study tested six open-weight configurations—GPT-5.6 Luna, GLM-5.3-Flash, gpt-oss-120b, gpt-oss-20b, gemma-4-31b, and qwen3-8b—using 225 facts that changed after February 16, 2026. The results showed that models often answer based solely on search snippets without opening the source pages; under the same set of search results, the proportion of turns in which no page was opened ranged from 2.6% to 76%, and when Luna used its built-in search, 53.6% of turns relied only on snippets. When answering from snippets alone, outdated answers accounted for 6.4% and misleading citations for 6.4%; when pages were opened and cited, these two figures dropped to 1.3% and 2.3%, respectively. The study also found that placing the correct page directly into the prompt significantly reduced errors, but some models still favored old information even when shown new facts. Currently, this research has been reported by a single source, with no subsequent developments yet.

Helion supports joint search compiler control and kernel configuration

Helion now supports incorporating compiler control parameters and kernel configurations into a single search. According to a PyTorch Blog article dated October 19, 2026, PyTorch Helion searches ptxas compiler control parameters through NVIDIA CompileIQ, jointly with the original kernel configuration search, further tapping performance headroom on about 27 kernels that have already been pre-tuned. CompileIQ packages tuning results as a portable Advanced Control File (ACF); Helion supports both specifying a fixed ACF and searching multiple ACFs together as one dimension of autotuning. These compiler controls have been exposed by ptxas since CUDA 13.3. There are currently no subsequent developments.

View story:Helion supports joint search of compiler controls and kernel configurations

TinyFish makes search and scraping free

TinyFish announced that it will waive retrieval fees for Search and Fetch within the limits. According to a MarkTechPost report, Search's free limit is 30 requests per minute and 500 per hour, while Fetch's is 150 URLs per minute and 1,000 per day. The report also notes that free retrieval does not eliminate the inference costs of downstream models: the same article of about 4,300 characters returns an estimated 1,184 to 42,774 tokens across different providers, and three pages of unfiltered content could fill a 128K context window. In the September 28, 2026 Artificial Analysis snapshot, TinyFish Search scored 71 at $9.30 per 1,000 tasks, the lowest total cost among the displayed configurations but also the lowest score, with each task taking about 59 seconds. There are currently no subsequent developments.

View story:TinyFish makes Search and Fetch free

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.

Trendos co-founder proposes a way to judge AI search visibility

Trendos co-founder Gintare Rimolaityte proposes that whether a brand is mentioned in AI search depends on five key sources: its official website, PR, review platforms such as Trustpilot and G2, affiliates, and social media; content should answer questions directly in an FAQ style rather than stuffing keywords. Trendos is an AI search visibility platform that, by scraping LLM conversations at scale, helps brands monitor and optimize how they appear in AI search across ChatGPT, Gemini, Claude, Perplexity, and others. The above content comes from an interview report published on October 17, 2026; no subsequent developments have been seen so far.

View story:Trendos co-founder proposes criteria for judging AI search visibility

Imperial College study reveals that search-augmented LLMs cite sources without reading them

On October 16, 2026, three authors from the Department of Computing at Imperial College London published the paper "Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available Evidence," investigating why search-augmented LLMs frequently cite web pages they never actually opened. The study tested six open-weight configurations—GPT-5.6 Luna, GLM-5.3-Flash, gpt-oss-120b, gpt-oss-20b, gemma-4-31b, and qwen3-8b—using 225 facts that changed after February 16, 2026. The results showed that models often answer based solely on search snippets without opening the source pages; under the same set of search results, the proportion of turns in which no page was opened ranged from 2.6% to 76%, and when Luna used its built-in search, 53.6% of turns relied only on snippets. When answering from snippets alone, outdated answers accounted for 6.4% and misleading citations for 6.4%; when pages were opened and cited, these two figures dropped to 1.3% and 2.3%, respectively. The study also found that placing the correct page directly into the prompt significantly reduced errors, but some models still favored old information even when shown new facts. Currently, this research has been reported by a single source, with no subsequent developments yet.

View story:Imperial College London Study Reveals Search-Augmented LLMs Cite Sources Without Reading Them

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.

English translation is being prepared.

View story:English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

View story:English translation is being prepared.