DiscoveryRSI：用递归自我改进做科研假设生成
一篇把递归自我改进用在做科学假设上的论文，27B 模型在假设命中率上超过了 GPT-6 和 Claude Opus 5，思路挺有意思。
一篇新论文提出 DiscoveryRSI，把递归自我改进（RSI）应用于生命科学四个领域的科研假设生成。其 27B 模型生成的假设与训练截止后发表的研究吻合率为 6.3%，高于 GPT-6 的 2.5% 和 Claude Opus 5 的 2.3%。系统通过多智能体进化搜索构建假设树，并将选中的研究方向转为可执行任务，每轮运行后给贡献假设分配信用、重放研究流程找出有效策略与反复失败。两轮改进后自动评估的假设质量从 4.86 升至 5.39，可证伪性提升最明显。论文编号为 arXiv:2610.23839。
Recursive self-improvement is one of the most discussed ideas in AI right now. I am particularly interested in how it applies to science. I saw this really cool new paper with neat ideas, especially on hypothesis generation. A good read. Specifically, they propose DiscoveryRSI, which applies RSI to scientific hypothesis generation in four life-science domains. Its 27B model produced hypotheses that match research published after its training cutoff 6.3% of the time, compared with 2.5% for GPT-6 and 2.3% for Claude Opus 5. The system grows trees of hypotheses with multi-agent evolutionary search and turns the chosen investigations into executable tasks. After each run, it assigns credit to the hypotheses that contributed, replays the research harness to find productive strategies and repeated failures, and applies accepted improvements to new investigations. Automated hypothesis quality rose from 4.86 to 5.39 after two rounds, with the largest gains in falsifiability. arxiv.org/abs/2610.23839 Chat with Paper: academy.dair.ai/papers/discove… 💬 4 🔄 0 ❤️ 3 👀 983 📊 4 ⚡
