{"slug":"web-search","label":"Web Search","item_count":3,"day_count":3,"source_count":3,"first_seen":"2026-10-17T20:30:24+00:00","last_updated":"2026-10-27T17:25:18+00:00","generated_at":"2026-10-28T00:13:55.337169+00:00","sources":["arxiv_agent_systems_research","hackernews_ai","search_cn_open_weight_labs"],"days":[{"date":"2026-10-17","items":[{"title":"DeepSeek prices web search for AI agents at $0.75 per 1,000 calls","url":"https://news.google.com/rss/articles/CBMiigFBVV95cUxON1poTVZpWnR5dFNydER0dTFQVmZmZnBDTFhrYl8xWEpiWmNnRzBYZWFMdjAwNjR4SEljQzUzZFN5aVRZbW05eHE2bDN4amJ0c2s3TkI4dFl6R2QzbmtOQWFxM2pWTmZzd1BtM1lhd2gzWXVTRHNJT0JHR21GSVZ2WHl2bG02UFIwMHc?oc=5","source":"search_cn_open_weight_labs","type":"news","summary_1line":"DeepSeek prices web search for AI agents at $0.75 per 1,000 calls PPC Land","why_it_matters":"Matches feed focus: agent.","sid":"dd757ca1b3c6b43c","published":"2026-10-17T20:30:24+00:00","editor_note":"Sets a concrete per-call price for agent web search."}]},{"date":"2026-10-26","items":[{"title":"LongSearchEval: Evaluating Long-Horizon Web Search Capabilities of Large Language Models via a Trajectory-Aware Agent Framework with Failure-Node Localization","url":"http://arxiv.org/abs/2610.35150v1","source":"arxiv_agent_systems_research","type":"paper","summary_1line":"Long-horizon web search requires LLM-based agents to integrate information across web pages through extended interactions under task-specific constraints. Evaluating this capability is important not only for measuring...","why_it_matters":"Matches feed focus: agent, evaluation.","sid":"5f97c21b490b1ce9","published":"2026-10-26T10:15:38+00:00","editor_note":"Adds an evaluation framework that localizes failures in multi-step search."}]},{"date":"2026-10-27","items":[{"title":"I benchmarked 4 web search APIs for AI agents on 30 live queries","url":"https://github.com/psinglap/websearch-api-eval","source":"hackernews_ai","type":"news","summary_1line":"I benchmarked 4 web search APIs for AI agents on 30 live queries","why_it_matters":"Matches feed focus: agent.","sid":"e3636bb8c76777d4","published":"2026-10-27T17:25:18+00:00","editor_note":"First hands-on comparison of search APIs on live queries."}]}],"editorial":{"tldr":"DeepSeek priced web search for agents at /bin/bash.75 per 1,000 calls on Oct 17, making search a metered line item. A long-horizon eval paper followed on Oct 26.","stale":false,"whats_new":"A GitHub benchmark compares 4 web search APIs for AI agents on 30 live queries, the first head-to-head comparison in this thread.","why_it_matters":"Search API choice now affects agent cost and answer quality, and neither the price point nor the benchmark is independently verified yet.","take_for_builders":"Run your own production queries against your current search API and one alternative, tracking cost per 1,000 calls and answer quality before switching.","status":{"state":"Developing","tone":"rising","changed":"2026-10-27","detail":"Pricing, an evaluation framework and a hands-on API benchmark have appeared, but the sources are thin and unconfirmed."},"beats":[{"kicker":"PRICING","tone":"launch","headline":"DeepSeek prices agent web search at $0.75 per 1,000 calls","sids":["dd757ca1b3c6b43c"]},{"kicker":"EVALUATION","tone":"rising","headline":"LongSearchEval targets long-horizon search failures","sids":["5f97c21b490b1ce9"]},{"kicker":"NOW","tone":"now","headline":"Community benchmark pits 4 search APIs against 30 live queries","sids":["e3636bb8c76777d4"]}],"open_questions":["Do the benchmark's API rankings hold on a larger or different query set?","Do other search API vendors respond to DeepSeek's per-call price?","Is LongSearchEval adopted to compare search-agent systems?"],"generated_at":"2026-10-28T00:13:28+00:00"}}