Research insights, project notes, and updates from pAI.
Sun Jun 21, 2026 / Pierfrancesco Beneventano and Tomer Galanti on behalf of the authors
We released a revised preprint of Distribution-Aware Algorithm Design with LLM Agents, joint work by Saharsh Koganti, Priyadarsi Mishra, Pierfrancesco Beneventano, and Tomer Galanti. The paper studies...
Mon Jun 8, 2026 / Tomer Galanti
Tomer Galanti has written a clear explainer of Distribution-Aware Programming, the blog post accompanying the paper Distribution-Aware Algorithm Design with LLM Agents. The post explains the central i...
Wed May 13, 2026 / Varun Sunkaraneni, Pierfrancesco Beneventano, Riccardo Neumarker, Tomaso Poggio, and Tomer Galanti
We released Agentic Systems as Boosting Weak Reasoning Models, a preprint studying when committees of weak reasoning-model calls can approach the performance of much stronger models. The core message...
Apr 2026 / Pierfrancesco Beneventano, Riccardo Neumarker, Mahmoud Abdelmoneum, and collaborators
We released Agent Systems for Academic Research Automation: An Evolving Survey, a living survey of agentic systems that produce scholarly artifacts such as papers, reviews, experiments, and rebuttals....
Tue Mar 31, 2026 / Pierfrancesco Beneventano on behalf of the pAI Team
Two new ways to run the pAI/MSc research pipeline are now available: a Claude Code skill and an OpenClaw plugin. Both wrap the same core pipeline — 22 agents, 29 backtested prompts, multi-round person...
Sat Mar 21, 2026 / Pierfrancesco Beneventano on behalf of the pAI Team
pAI/MSc is now online. You can read the technical report or browse the GitHub repository. This first public release is an open-source, customizable, modular multi-agent system for academic research wo...
