Tag
LiteResearcher is a scalable reinforcement learning training framework designed for deep research agents.
Anthropic has launched Claude Science, an AI workbench for scientists with over 60 built-in research skills. It supports local deployment and HPC clusters, and can autonomously draft computing tasks and review results.
Microsoft Research introduces Arbor, a generalist autonomous research agent that uses persistent hypothesis-tree refinement for cumulative learning, outperforming Codex and Claude Code across six research tasks and achieving 86% Any-Medal on MLE-Bench Lite.
DeepResearch is an open-source multi-agent research tool built with Spring AI Alibaba that converts queries into structured reports using dynamic planning, multi-agent roles, hybrid RAG, and Docker-based execution.
Tavily announces its Deep Research API, a single endpoint that performs multi-step research end-to-end and returns structured, source-cited reports. The API supports custom files, output schemas, and configurable research modes.
An autonomous research agent built by Weco became the top contributor by volume of merged records in OpenAI's Parameter Golf competition, demonstrating effective human-agent collaboration.
Skill RSI is a free tool that recursively evaluates and improves AI skills via procedural evaluations and a research agent, supporting standalone or Codex plugin usage.
LangChain showcases a macroeconomic research agent built with Deep Agents, LangSmith, and the You.com Finance Research API that analyzes GDP data, detects anomalies, and investigates structural and cyclical drivers at the sector level, producing structured, cited briefings.
Tabstack launches a research agent that provides cited answers in a single API call, aimed at developers and researchers.
A developer built a fully traceable and forkable research agent using Active Graph and monid_ai, ensuring every claim is natively traced to its source, and got it working in about 30 minutes.
Built a fully traceable and forkable research agent using Active Graph and monid_ai that ensures every claim has receipts, avoiding the black-box problem of typical agents.
Hermes Agent now integrates with xAI Grok Subscription, allowing users to add an X Research Agent profile to monitor X while they work.
TIGER-AI-Lab releases OpenResearcher, an open-source agent designed to automate long-horizon deep research tasks.