Search “Search”

TinyFish releases technical guide for production-grade agent search architecture

On October 23, 2026, TinyFish released two technical guides: one defines a production-grade agentic search architecture, and the other summarizes lessons learned from building a deep research system. According to a MarkTechPost report, the architecture is built on four web primitives—TinySearch, TinyFetch, TinyBrowser, and TinyAgent—and runs a seven-stage control loop around a foundation model, covering task definition, retrieval planning, tool routing, evidence evaluation, and failure retry. In OpenBenchmarks tests with a fixed gpt-5.6-sol model and 100 tasks, the search-plus-fetch configuration achieved a 79.0% completion rate, with a median task cost of $0.050 and a runtime of 24 seconds; the search-only configuration achieved a 59.3% completion rate. Currently, this event has only the single source report mentioned above, and there have been no subsequent developments.

View story:TinyFish Releases Technical Guide for Production-Grade Agentic Search Architecture

Gemini launches ability to reference Google Maps searches and saved places

Gemini has launched the ability to reference Google Maps search history and saved places. According to related reports, after user authorization, Gemini can now read Google Maps search history and saved places, and combine them with Google Calendar to provide users with personalized recommendations for the day. This capability has currently been announced as launched by Gemini, and there are no further developments as of yet.

Gemini can reference Google Maps search and saved places

Gemini has launched the ability to reference Google Maps search history and saved places. According to related reports, after user authorization, Gemini can now read Google Maps search history and saved places, and combine them with Google Calendar to provide users with personalized recommendations for the day. This capability has currently been announced as launched by Gemini, and there are no further developments as of yet.

View story:Gemini launches ability to reference Google Maps searches and saved places

MiniMax says M3.1 Flash tops search capability efficiency leaderboard

On October 19, 2026, MiniMax released the M3.1 Flash model. The company says it costs one-third as much as M3 and is 3 times faster, with a unified API price of $0.15/$0.60 per 1M input/output tokens and cached reads at $0.015 per 1M tokens; it had previously been tested anonymously on OpenRouter under the name Space Bunny, ranking first on the model leaderboard for 10 consecutive days. On October 20, the model launched on platforms including Ollama, GMI Cloud, Cline, and OpenClaw, with Cline offering it for free; third-party testing compared it with Claude Opus 5.5, and both completed a Three.js task on the first attempt. On October 21, Parallel Web Systems' search capability efficiency leaderboard ranked it first. On October 22, MiniMax announced that Inferact had become its API launch partner, and the model launched on Runware. On October 23, MiniMax said SGLang and Miles provided support on the first day of release.

View story:MiniMax releases the M3.1 Flash model

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.

Artificial Analysis Adds DeepSeek Search to Its Search Index Evaluation

Artificial Analysis has added DeepSeek Search to its search index evaluation. The evaluation results from October 22, 2026 show that DeepSeek Search scored 69 on the index, ranking 17th among 27 search products, and is the lowest-priced paid search API on the list: charging $0.75 per 1k searches, with a cost of about $0.032 per task, making it the 5th cheapest among the 27 products. In terms of accuracy, it scores 70% on AA-Omniscience, ranking 10th, but only 63% on BrowseComp, which requires multi-hop reasoning, ranking 25th. In addition, each search returns about 7k tokens, raising the model cost to the 2nd highest on the list. There are currently no further developments.

Artificial Analysis includes DeepSeek Search in its search index evaluation

Artificial Analysis has added DeepSeek Search to its search index evaluation. The evaluation results from October 22, 2026 show that DeepSeek Search scored 69 on the index, ranking 17th among 27 search products, and is the lowest-priced paid search API on the list: charging $0.75 per 1k searches, with a cost of about $0.032 per task, making it the 5th cheapest among the 27 products. In terms of accuracy, it scores 70% on AA-Omniscience, ranking 10th, but only 63% on BrowseComp, which requires multi-hop reasoning, ranking 25th. In addition, each search returns about 7k tokens, raising the model cost to the 2nd highest on the list. There are currently no further developments.

View story:Artificial Analysis Adds DeepSeek Search to Its Search Index Evaluation

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

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.

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 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