{"slug":"deep-research","label":"Deep Research","item_count":3,"day_count":3,"source_count":3,"first_seen":"2026-05-27T07:45:00+00:00","last_updated":"2026-06-15T13:56:33+00:00","generated_at":"2026-06-15T15:11:20.746371+00:00","sources":["arxiv_cs_cl","aws_ml_blog","infoq_ai_ml"],"days":[{"date":"2026-05-27","items":[{"title":"Sarang Kulkarni on Lessons from Building Deep Research Agents in Production","url":"https://www.infoq.com/news/2026/05/kulkarni-deep-research-agents/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI%2C+ML+%26+Data+Engineering","source":"infoq_ai_ml","type":"news","summary_1line":"Deep Research Agentic Systems are AI Agents designed to conduct multi-step research for complex tasks using dynamic reasoning, multi-hop information retrieval, and generate structured analytical reports. Sarang Kulkar...","sid":"db3f935ead18d952","published":"2026-05-27T07:45:00+00:00","editor_note":"Opens the thread with production lessons and a working definition of deep research agentic systems."}]},{"date":"2026-06-08","items":[{"title":"Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback","url":"http://arxiv.org/abs/2606.09748v1","source":"arxiv_cs_cl","type":"paper","summary_1line":"Existing benchmarks for deep research agents (DRAs) assess only single-shot outputs, ignoring a key question: can DRAs improve their reports when guided by feedback? To investigate this, we conduct a multi-turn evalua...","sid":"c5cd09a4f478ae3e","published":"2026-06-08T17:08:36+00:00","editor_note":"Names the evaluation gap — existing benchmarks test only single-shot output — and proposes multi-turn evaluation under process-level feedback."}]},{"date":"2026-06-15","items":[{"title":"Build context-rich research agents with Deep Agents and Bedrock AgentCore","url":"https://aws.amazon.com/blogs/machine-learning/build-context-rich-research-agents-with-deep-agents-and-bedrock-agentcore","source":"aws_ml_blog","type":"news","summary_1line":"In this post, you'll build a competitive research agent that demonstrates this pattern end to end. This walkthrough targets developers building multi-step AI workflows who need isolated execution environments for thei...","why_it_matters":"Matches feed focus: agent.","sid":"2f2101adc8737656","published":"2026-06-15T13:56:33+00:00","editor_note":"First concrete end-to-end build pattern, on AWS Deep Agents and Bedrock AgentCore."}]}],"editorial":{"tldr":"Deep research agents — systems that run multi-step research using dynamic reasoning and multi-hop retrieval — moved from field notes toward repeatable practice over three weeks. InfoQ opened with Sarang Kulkarni's production lessons on building them; an arXiv paper then flagged an evaluation gap, arguing existing benchmarks only score single-shot output and proposing multi-turn evaluation under process-level feedback; AWS closed with an end-to-end build using Deep Agents and Bedrock AgentCore.","stale":false,"whats_new":"The latest beat is AWS's hands-on walkthrough building a competitive research agent end to end on Deep Agents plus Bedrock AgentCore — the thread's first concrete, platform-specific build pattern, after the earlier production-lessons and evaluation-method posts.","why_it_matters":"Deep research agents are maturing into something an engineer can actually ship: there's now a managed-cloud build pattern to copy and a multi-turn evaluation method to judge whether the agent improves under feedback rather than just its one-shot answer.","generated_at":"2026-06-15T15:11:00+00:00"}}