@kuzved1988.bsky.socialChatGPT Work, Deep Research и агенты: как выбрать инструмент под задачу
Понятия «агент», «Work» и «Deep Research» в ChatGPT нередко смешивают, хотя каждый из них решает разные задачи — разобраться помогут их отличия и базовые меры безопасности.
@kuzved1988.bsky.socialАвтономные системы глубоких исследований меняют подход к науке
Появился новый класс автономных ИИ-агентов для сложных многошаговых исследовательских задач, объединяющих рассуждение, планирование и использование инструментов.
@devstackdaily.bsky.socialA new paper introduces Proof-of-Use, a reinforcement learning framework that tackles tool-call hacking in deep research agents by enforcing causal dependency between retrieved evidence and reasoning.
#AIResearch #MachineLearning #DeepResearch #ReinforcementLearning
https://arxiv.org/abs/2510.10931
@ossradarai.bsky.socialNew arXiv benchmark Dr-CiK tests whether deep research agents can find, filter, and distill forecasting-relevant context from document corpora rather than receiving it pre-selected. Results show high-quality context…
#OpenSourceAI #DeepResearch #TimeSeries
https://arxiv.org/abs/2605.27904
@ossradarai.bsky.socialNew arXiv paper VideoResearchAgent introduces a training framework for agents that autonomously discover and reason over open-web video, using controllable task synthesis and sim-to-real RL to…
#OpenSourceAI #DeepResearch #VideoReasoning #ReinforcementLearning
https://arxiv.org/abs/2610.04911
@aliamartin.bsky.social
@useapi.netAutomate NotebookLM over REST on your own Google account: notebooks, chat with citations, Deep Research, and Audio Overviews, Video Overviews, slides and quizzes. Full tutorial with curl:
@k-i-news.bsky.socialExa startet Agent Ultra: Subagenten durchsuchen tausende Quellen parallel – für vollständige Listen statt Prosa. Laut Exa schlägt es Opus 5.5 und GPT-6 Astra auf 4 Benchmarks. Vollständigkeit ist der Hebel, Kosten der Haken. #DeepResearch
Mehr von mir: linkedin.com/in/maurice-putinas
@trustinsights.bsky.socialUntil earlier this year, Trust Insights didn't answer RFPs. On So What?, Katie Robbert and John Wall talked about what changed: deep research on the prospect before writing anything. (1/3)
@trustinsights.bsky.socialTomorrow, 9.24.2026, CEO Katie Robbert and Head of Business Development John Wall will be going over just how much the sales process has changed. Not only because of AI, but because of deep research specifically.
1pm ET. YouTube Live. We will see you then!
@rurou-creator.bsky.social新しい記事を公開しました🎉
ChatGPTのCodexとDeep Research、この2つであなたの仕事の「考える」と「動く」がまるごと変わる
note.com/t894he1och06...
@vicky-grok.bsky.social29K+ GitHub stars and 4K+ forks.
The project is also Apache-2.0 licensed and actively maintained.
Basically, your research question becomes a workflow. 🔥
#GPTResearcher #AI #DeepResearch #AIAgents #OpenSource #LLM #Research #MachineLearning #AIResearch #DeveloperTools
@matthiasschuessler.chHeute räume ich ein tiefsitzendes Missverständnis aus der Welt: Nein, die KI nimmt uns den Recherchearbeit nicht komplett ab – auch mit Features wie der #DeepResearch nicht. Ein paar elementare Überlegungen, wie Informationsbeschaffung und Schreiben zusammenhängen. #clickomaniach
@liasmart.bsky.socialResearch-Agents wie Gemini & Manus recherchieren jetzt mehrstufig für dich — Dutzende Quellen, strukturierte Ergebnisse, automatisch. Stunden → Minuten. 🔎 maikmarx.de #KITools #DeepResearch
🤖 KI-generiert
