Skip to content
K = 0.731
← All topics

Agents

Models that plan, call tools and finish multi-step tasks on their own: from Claude Code and Manus to agent frameworks and benchmarks.

170 picksLast 30 days 93 itemsCollected 664 items

New

Picks archive · page 8

5/22Fri
  1. Mistral AI82

    Mistral releases Mistral Medium 3.5 and Vibe cloud-based remote agent

    Mistral has released Mistral Medium 3.5, a dense 128B model with open weights under a modified MIT license. It becomes the default model in Mistral Vibe and Le Chat, with API pricing of $1.50 per million input tokens and $7.50 per million output tokens.

    Why it matters: Mistral is bringing its coding agent to the cloud while opening the weights of a 128B model, giving readers a basis for judging the feasibility of self-hosted coding agents.

  2. Mistral AI62

    Mistral launches Connectors in Studio with built-in and custom MCP support

    Mistral has released Connectors in Studio as a public preview. Built-in and custom MCP connectors can be used through the API or SDK with all models and agent calls. New direct tool calls let developers decide when tools are invoked, and human-in-the-loop approval lets applications confirm before a tool executes.

    Why it matters: The source gives code paths for registering and calling connectors and for human approval, helping readers assess changes to enterprise tool integration.

5/20Wed
5/19Tue
  1. Google DeepMind60

    Google DeepMind's Co-Scientist accelerates discovery of genetic clues to reversing cellular aging

    Google DeepMind biologists Omar Abudayyeh and Jonathan Gootenberg used Co-Scientist to support aging research. After scanning tens of thousands of papers, the tool proposed more than 20 new candidate genetic factors. Lab tests validated several hypotheses, successfully making cells younger and improving their overall function. Co-Scientist also analyzed large-scale genetic-screening data, reducing data and literature linkage work that could take up to six months to just days.

    Why it matters: The source reports specific outputs and time comparisons from Co-Scientist's role in aging research, showing how AI agents contribute to scientific hypothesis generation.

5/18Mon
  1. Google DeepMind62

    Google DeepMind brings real-world Street View scenes to Project Genie

    Google DeepMind has added Street View scene anchoring to the experimental Project Genie prototype. It can generate interactive worlds based on real locations in the United States, with optional styles such as Ocean World, Desert Sands, Stone Age, and B&W film.

    Why it matters: The source explains Project Genie's capabilities and availability with Street View, offering a view of how world models may be deployed.

5/17Sun
5/16Sat
  1. Google DeepMind88

    Google DeepMind releases Gemini 3.5 Flash for agents and coding

    Google DeepMind has released Gemini 3.5 Flash, the first model in the Gemini 3.5 family, positioning it as a frontier model for agents and coding. It is available starting today in the Gemini app, AI Mode in Google Search, Google Antigravity, the Gemini API, and Gemini Enterprise.

    Why it matters: Gemini 3.5 Flash beats 3.1 Pro on coding and agent benchmarks and includes speed and cost comparisons, helping readers assess its potential for long-horizon tasks.

5/12Tue
  1. Google DeepMind71

    Google DeepMind releases Co-Scientist multi-agent research system

    Google DeepMind has published research on Co-Scientist in Nature. Built on Gemini, it is a multi-agent AI system that iteratively generates, debates, and evolves scientific hypotheses.

    Why it matters: The article describes the multi-agent system's three-stage architecture and deployments in several labs, explaining how AI contributes to scientific hypothesis generation.

5/6Wed
  1. Google DeepMind80

    Google DeepMind reviews a year of AlphaEvolve, from mathematical discoveries to TPUs and commercial deployment

    Google DeepMind has published a one-year impact review of AlphaEvolve, the Gemini-powered coding agent. It has expanded from exploring open problems in mathematics and computer science to becoming a core component of Google's infrastructure.

    Why it matters: The official review summarizes AlphaEvolve deployments over its first year, helping readers assess how algorithmic agents are being used in science and infrastructure.

4/30Thu
  1. Google DeepMind62

    Google DeepMind launches AI co-clinician research program

    Google DeepMind has announced an AI co-clinician research program exploring a “triple-care” model in which AI agents assist with patient care under clinical supervision. In blind evaluation of 98 real primary-care queries, the system had no critical errors in 97 cases, and doctors preferred its responses to those from existing evidence-synthesis tools. It also outperformed other frontier models on open-ended medication questions in OpenFDA's RxQA.

    Why it matters: Google DeepMind reports results from physician blind reviews, RxQA, and simulated remote consultations, offering a view of current medical-AI capabilities.

  2. Google Research62

    Four ways scientists are using Google's Empirical Research Assistance

    Google Research summarizes four areas where scientists use Empirical Research Assistance (ERA): in public health, the team submits weekly influenza forecasts for U.S. states.

    Why it matters: Google uses four real research projects to show ERA deployments in epidemic forecasting, cosmology, carbon monitoring, and neuroscience, illustrating how AI-assisted research is being used.

4/27Mon
  1. Mistral AI71

    Mistral AI releases public preview of Workflows

    Mistral AI has released Workflows as a public preview of its enterprise AI orchestration layer. It offers persistent execution, observability, and fault tolerance to take AI processes from proof of concept into production. Organizations including ASML, ABANCA, CMA-CGM, France Travail, La Banque Postale, and Moeve already use it to automate key workflows.

    Why it matters: The source describes Workflows' persistent execution, observability, and human approval features, helping readers assess the orchestration requirements for enterprise AI deployments.

4/22Wed
  1. Google Research62

    Google proposes ReasoningBank, helping agents learn from successes and failures

    In an ICLR paper, Google Research proposes ReasoningBank, an agent-memory framework that extracts high-level, structured reasoning memories from successful and failed experiences. Its code is open-source.

    Why it matters: The paper describes a closed loop for extracting reasoning memories from successes and failures, with success-rate and step-count results on WebArena and SWE-Bench-Verified.

4/3Fri
3/29Sun
  1. Google DeepMind62

    Google DeepMind redesigns the mouse pointer for the AI era, rolling out first in Chrome and Googlebook

    Google DeepMind has published four interaction principles for AI pointers and demonstrated an experimental Gemini-powered pointer. In Google AI Studio, users can edit images or find places on a map by pointing and speaking.

    Why it matters: Google DeepMind lays out four principles for pointer interaction and previews deployments in Chrome and Googlebook, showing a path from prompts toward pointing and voice.

3/25Wed
  1. Google Research62

    Google releases Vibe Coding XR, turning natural language into Android XR apps with Gemini and XR Blocks

    Google has released the Vibe Coding XR workflow, combining Gemini's long-context reasoning with the XR Blocks framework, based on WebXR, three.js, and LiteRT.js, to turn natural language directly into physics-aware Android XR apps. Google says the process takes under 60 seconds.

    Why it matters: Google combines Gemini and XR Blocks into a workflow for generating XR apps from a single sentence and reports preliminary VCXR60 benchmark results, offering a view of the changing barrier to spatial-computing prototypes.

3/18Wed
  1. Mistral AI62

    Mistral AI launches Forge, an enterprise model-training system

    Mistral AI has released Forge, a system that lets enterprises build frontier-level AI models from their own proprietary knowledge. It spans pretraining, post-training, and reinforcement learning; supports dense and MoE architectures; and accepts multimodal inputs.

    Why it matters: The source details the stages of training frontier models on enterprise data and names organizations already involved, helping readers assess the path and barriers to building models in-house.

3/11Wed
1/28Wed
  1. Mistral AI62

    Mistral releases Vibe 2.0, a terminal coding agent powered by Devstral 2

    Mistral has released Vibe 2.0, a terminal-native coding agent powered by the Devstral 2 family. New features include custom subagents, multiple-choice clarification, slash-command skills, a unified agent mode, and automatic updates.

    Why it matters: The official release details Vibe 2.0's custom subagents, slash-command skills, and billing, helping readers assess how to use and budget for a terminal coding agent.

12/9Tue
  1. Mistral AI82

    Mistral releases Devstral 2 coding models and Mistral Vibe CLI

    Mistral AI has released the next-generation Devstral 2 coding-model family, comprising Devstral 2 at 123B and Devstral Small 2 at 24B. Both are open-source, under modified MIT and Apache 2.0 licenses respectively.

    Why it matters: The article reports the two open coding models' sizes, licenses, SWE-bench results, and head-to-head comparisons with closed models, helping readers assess the current level of open coding agents.