The PromptBio Platform integrates conversational artificial intelligence and multi-agent orchestration, unifying workflows for conversational research, bioinformatics, and drug discovery to transform scientific questions into actionable insights.
Researchers developed the Multistep Multimodal Multiomic Agentic (M3A) Framework. This framework supports large language model-driven reasoning across persistent multimodal data and captures agentic reasoning behaviors in both autonomous and human-AI copilot settings for evaluating AI systems in biological discovery.
Evaluation found that current artificial intelligence agents competently perform broad, systemic exploration of complex multi-omic data. However, human domain experts remain crucial for providing methodological guidance and synthesizing biological insights across various analyses.
CosmoEvolve demonstrated autonomous data analysis of ACT DR6 data, identifying non-trivial pair- and scale-dependent behavior and producing analysis-grade diagnostics.
An arXiv paper analyzed production data from Perplexity's Search and Computer products. The study found Perplexity's Computer, an agentic system, handled more autonomous work per user session and resulted in lower dissatisfaction rates compared to its Search product. It also reported reductions in task completion time and cost, enabling users to reallocate efforts towards higher-order verification and extension tasks.
The adoption of autonomous science discovery presents specific challenges, including issues with research reproducibility due to the stochastic nature of AI reasoning. Ethical considerations regarding inventorship, safety, and the changing role of human scientists also arise.
A guide evaluates ten artificial intelligence tools for universities and research institutions in 2026. It reviews each tool based on criteria including accuracy, citation support, ease of use, and security to support informed decisions for AI adoption.
Microsoft released new internally developed artificial intelligence models and introduced a personal work agent.
The combined team at Reka will focus on developing the World Language Action Model (WLAM), an omni-model designed to be trained on physical world data for realistic simulation and planning.
Researchers introduced LLM-AL, an LLM-based active learning framework that proposes experiments directly from text-based descriptions. It leverages LLMs' pretrained knowledge and operates in an iterative few-shot setting.
- LLM-AL outperformed traditional machine learning models in active learning across four materials science datasets.
- The framework significantly decreased the experimental effort required, reducing the number of experiments needed to reach top-performing candidates by over 70%.
- LLM-AL performs broader and more exploratory searches while still achieving optimal results with fewer iterations.
- Despite the inherent non-determinism of large language models, LLM-AL demonstrated performance stability across runs, aligning with typical observations for traditional machine learning approaches.
Sources
- PromptBio Launches Agentic AI Platform to Accelerate Scientific ...
New multi-agent AI platform combines conversational research, bioinformatics, and drug discovery workflows to transform scientific questions into actionable insights within a unified environment. The PromptBio Platform combines conversational AI with multi-agent orchestration to accelerate discovery from hypotheses to insights.
- AI Autonomous Science Discovery Could Redefine How ...
AI Autonomous Science Discovery is rapidly transforming scientific research, moving from AI as a calculation tool to an autonomous agent capable of proposing hypotheses, designing experiments, and writing manuscripts without human intervention. This shift, exemplified by systems like Robin and Google DeepMind's Co-Scientist, dramatically reduces discovery time and uncovers cross-disciplinary connections humans often miss. However, it introduces challenges such as reproducibility issues due to stochastic reasoning paths and ethical questions regarding inventorship, safety, and the evolving…
- AI Agents Reshape Knowledge Work, Increasing Autonomy and ...
An arXiv paper quantifies how agentic systems change knowledge work, using production data from Perplexity's Search and Computer products. The paper indicates that Computer performs significantly more autonomous work per user session and has lower dissatisfaction rates compared to Search. It also reports substantial reductions in task completion time and cost, with users shifting towards higher-order verification and extension tasks.
- Evaluating agentic AI for biological discovery in autonomous and copilot settings
Advances in large language models (LLMs)-based artificial intelligence (AI) agents have improved their ability to execute structured analytical workflows, including standard bioinformatic pipelines for biological discovery. However, computational biology rarely consists of deterministic pipeline execution alone. Biological datasets are heterogeneous and noisy, and meaningful discovery often requires open-ended hypothesis generation and iterative reasoning over multimodal evidence. These challenges are particularly evident in multi-omic studies, where paired molecular modalities and…
- Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology
Recent advances in artificial intelligence (AI) agents are pushing AI beyond tools toward autonomous scientific discovery. We discuss two complementary agentic systems for cosmology: \texttt{CMBEvolve}, which targets tasks with explicit quantitative objectives through LLM-guided code evolution and tree search, and \texttt{CosmoEvolve}, which targets open-ended scientific workflows through a virtual multi-agent research laboratory. As preliminary demonstrations, we apply \texttt{CMBEvolve} to out-of-distribution detection in weak-lensing maps, where it iteratively improves the benchmark score…
- Best AI Tools for Universities & Research Institutions 2026 - Chitika
This guide evaluates the ten best AI tools available to universities and research institutions in 2026, reviewing each across criteria like accuracy, citation support, ease of use, and security, with the goal of aiding confident, well-informed AI adoption decisions. It highlights tools such as CustomGPT.ai for research knowledge management, ChatGPT for general writing, and Claude for nuanced document analysis. The article concludes with a buyer checklist, an ROI framework, a risk overview, and best practices for implementation, emphasizing that most AI risks are mitigable through thoughtful…
- AI News Roundup: May 26 – June 07, 2026
This AI News Roundup covers key developments from May 26 to June 07, 2026, including OpenAI's plans for a ChatGPT superapp overhaul, Anthropic's call for a coordinated AI pause plan, and SpaceX's AI compute deal with Google. Other significant news includes Japan's warning about becoming an "AI colony," South Korea's push for AI profit-sharing, and Microsoft's introduction of new in-house AI models and a personal work agent. The roundup also highlights developments in AI regulation, investment, and ethical considerations across various global entities.
- Reka and Moonvalley Join Forces to Advance Models and ...
Reka, an AI research lab, has partnered with Moonvalley, integrating their team of AI researchers and engineers to accelerate the development of models and infrastructure for physical AI. This merger brings experts from DeepMind, Meta, and Google to Reka, with Mateusz Malinowski and Mikołaj Bińkowski joining Reka's research leadership. The combined team will focus on the World Language Action Model (WLAM), an omni-model trained on physical world data for realistic simulation and planning in real-world scenarios.
- Training-free active learning framework in materials science with large language models
Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering, restricting their generalizability. Large language models (LLMs) offer a new paradigm by leveraging their pretrained knowledge and universal token-based representations to propose experiments directly from text-based descriptions. Here, we introduce an LLM-based active learning framework (LLM-AL) that operates in an iterative few-shot setting and benchmark it…
Also this week
- New AI Tools for the Future of Science - Google Blog
- deepmind.google
- I rebuilt Google's AI Co-Scientist (Nature 2026) as open source, cuz ...
- [Literature Review] LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
- LLM-Based Multi-Agent Decision-Making: Challenges and Future ...
- Multi Agent LLM Framework for Autonomous Decision Systems ...
- Multi-Agent Systems (MAS) in 2026: The Complete Guide | Santage
- Agentic material science - OAE Publishing Inc.
- Generative AI in Material Science Market Report 2026
- Agentic AI for Business Workflows 2026 | Involve Digital
- yutori.com
- 58 Grants, Fellowships and Awards Currently Open – June 7, 2026 ...
- mcdermottlaw.com
- Artificial Intelligence Research Initiatives (2026) | Granted AI
- AI Updates Today (June 2026) – Latest AI Model Releases - LLM Stats
- Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards