Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries

[2606.10402] Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2606.10402 (cs) [Submitted on 9 Jun 2026 ( v1 ), last revised 26 Aug 2026 (this version, v2)] Title: Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries Authors: Federico Bianchi , Yongchan Kwon , Aneesh Pappu , James Zou View PDF HTML (experimental) 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. Comments: Updated to correct a mistake Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2606.10402 [cs.CL] (or arXiv:2606.10402v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2606.10402 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Federico Bianchi [ view email ] [v1] Tue, 9 Jun 2026 04:25:28 UTC (724 KB) [v2] Wed, 26 Aug 2026 19:33:02 UTC (724 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-06 Change to browse by: cs cs.AI References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries#677637
• Diving into AI? Exploring the Potential for AI to Tackle Complex Water Quality Challenges.#25625
• MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution#1142950
• Bridging the Global Artificial Intelligence Divide#336525
• Artificial Intelligence Needs Sensors: Building the Data Layer for Artificial Intelligence-Accelerated Discovery#490884