# Agentic Discovery: Closing the Loop with Cooperative Agents

arXiv: https://arxiv.org/abs/2510.13081 · HTML: https://mlsanity.com/paper/2510.13081/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 6 of 6)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The strain on scientific publishing](https://mlsanity.com/paper/2309.15884/) (2023)
- [Empowering Scientific Workflows with Federated Agents](https://mlsanity.com/paper/2505.05428/) (2025)
- [MOFA: Discovering Materials for Carbon Capture with a GenAI- and Simulation-Based Workflow](https://mlsanity.com/paper/2501.10651/) (2025)
- [Spark-MPI: Approaching the Fifth Paradigm of Cognitive Applications](https://mlsanity.com/paper/1806.01110/) (2018)

## Built on by (most cited first, 2 of 2)

- [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026)
- [StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery](https://mlsanity.com/paper/2606.11851/) (2026)

## Abstract (arXiv)

As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, generating hypotheses, and designing experiments. We postulate that cooperative agents are needed to augment the role of humans and enable autonomous discovery. Realizing such agents will require progress in both AI and infrastructure.