@PhAILabs: Today we're releasing DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses. In our latest AI research ben…
Summary
PhAI Labs 发布 DiscoveryRSI：一种递归学习以发现有价值科学假设的方法，在其最新 AI 研究基准上以 6.3% 成绩登顶，约为 GPT 的 2.5 倍、Claude 的 2.7 倍，并同步开源论文、代码与模型，同时提供可实时在线观看的研究直播竞技场。
View Cached Full Text
Cached at: 10/20/26, 01:32 AM
🚀 Today we’re releasing DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses.
In our latest AI research benchmark, our DiscoveryRSI came out on top at 6.3% — about 2.5× GPT and 2.7× Claude.
You can also follow the research live — streaming now through October 21!
📡 Live Arena: https://foundry-arena.rsi-arena.workers.dev/arena 📄 Paper: https://arxiv.org/abs/2610.23839 💻 Code: https://github.com/Gen-Verse/DiscoveryRSI… 🤗 Models: https://huggingface.co/collections/Gen-Verse/discoveryrsi…
#Agents #ScientificDiscovery #RSI #AI
DiscoveryRSI · PhAI Labs
Source: https://foundry-arena.rsi-arena.workers.dev/arena
Live proposal stream
live
Up and down arrows move through the feed, Home and End jump to the ends, Enter opens the hypothesis on the research tree.
Similar Articles
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
DiscoveryRSI introduces a multi-agent evolutionary search framework with recursive learning to generate and refine valuable scientific hypotheses, achieving self-improvement gains and outperforming baseline research agents like GPT-6 and Claude Opus on life-science benchmarks, alongside a new DFM-Bench evaluation suite.
@MaxForAI: Tian Yuandong @tydsh's startup team Recursive @Recursive_SI released a milestone: an automated AI research system. In this system, AI can complete the entire research loop of 'propose ideas → implement → run experiments → verify → select next experiment based on results'. Results show that with clear objectives...
The Recursive team released an automated AI research system that can autonomously complete the research loop, surpassing existing human community solutions on multiple benchmarks. For example, on NanoGPT Speedrun it compressed training time from 79.7 seconds to 77.5 seconds, and on SOL-ExecBench it improved the score to 0.754.
@omarsar0: Recursive self-improvement is one of the most discussed ideas in AI right now. I am particularly interested in how it a…
The paper introduces DiscoveryRSI, a framework that applies recursive self-improvement to scientific hypothesis generation via multi-agent evolutionary search, harness replay and credit assignment, boosting hypothesis quality from 4.86 to 5.39 and reaching 6.3% correspondence with post-cutoff research across four life-science domains.
Benchmarking and Enhancing Agentic Causal Discovery
论文提出 Heuresis，一个使用匿名模拟数据的因果发现基准，用于评估 LLM 智能体在数据驱动下进行细粒度、证据驱动的因果发现调整能力。结果显示 GPT-6.1 Sol 在全部六个数据族上超过最佳算法选择，最难族上邻接 F1 提升 14%。
@nickscamara_: New discoveries are gonna come from models that can reason over the latest science The rate of scientific progress beco…
Firecrawl released a state-of-the-art research index for AI/ML papers, claiming 18% better recall on arXivQA than competitors, designed for autonomous research agents.