Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
Quick Answer
This paper shows that EinsteinArena, a platform for AI agents, has enabled decentralized scientific discovery, achieving 12 new state-of-the-art results, including improving the kissing number problem in dimension 11 from 593 to 604.
Quick Take
EinsteinArena, a platform for AI agents, has enabled decentralized scientific discovery, achieving 12 new state-of-the-art results, including improving the kissing number problem in dimension 11 from 593 to 604. This demonstrates the potential of collective AI-driven research through open collaboration among agents.
Key Points
- EinsteinArena hosts a live set of open problems for AI agents.
- Agents improved the kissing number problem's lower bound from 593 to 604.
- The platform emphasizes mathematical tasks with clear progress measurement.
- Decentralized discovery emerged from agent interactions and public discussions.
- 12 new state-of-the-art results were achieved by collaborative agent efforts.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 10402v1 Announce Type: new Abstract: Scientific discovery is often a collective process: researchers share partial results, inspect failed attempts, and build on each other's ideas over long time horizons. Recent AI systems have shown that language-model-based agents can make meaningful progress on open scientific problems, but most existing systems operate in isolation. In this paper, we present EinsteinArena, an agent-native platform for open distributed research and discovery.
EinsteinArena provides agents with a live set of open problems, each with a solid verifier, public leaderboard, and problem-specific discussion forum where agents can ask questions and share insights. We focus on mathematical tasks that have garnered substantial research interest, where progress can be measured unambiguously. As of May 2026, agents on EinsteinArena have discovered 12 new state-of-the-art results better than any previous human or AI solutions.
One notable example is the kissing number problem in dimension 11, where the platform improved the best known lower bound from 593 to 604. This advance did not come from a single agent or isolated run. Rather it arose through a sequence of submissions, public discussion, verifier refinement, and subsequent agent-to-agent borrowing of ideas.
These results provide evidence that decentralized scientific discovery can emerge from open interaction among autonomous agents in the wild, demonstrating a new paradigm for collective AI-driven research.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.