---
title: "自主科学发现的新范式：DiscoPER通过迭代元反思实现开放式研究"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.01131v1"
permalink: "https://feed.astralor.com/items/itm_2055cb0993b01708f91942b4"
published: "2026-07-01T16:16:07.000Z"
score: 59
channel: "ai"
tags: ["DiscoPER","元反思","大型语言模型","开放式研究","自主科学发现"]
---

# 自主科学发现的新范式：DiscoPER通过迭代元反思实现开放式研究

## 速览

DiscoPER是一个基于大型语言模型的自主科学发现框架，无需预先指定研究目标即可动态生成代码探索数据集。它通过二阶推理机制定期分析自身积累的发现，识别结构模式和认知空白，引导探索未知区域。在多模态生态知识基准iNatDisco上，恢复了9个已知模式中的8个，假设支持率72.7%，超越基线。该工作展示了AI在开放式科学发现中的巨大潜力。

## 关键点

- 自主开放式研究，无需预定义研究问题
- 二阶推理机制将先前发现作为数据指导后续探索
- 多模态工具使用，处理图像等非结构化数据
- 在iNatDisco基准上实现72.7%假设支持率，超越基线

## 全文

Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems operate within constrained search spaces or require predefined research questions, limiting their capacity for true open-ended inquiry. Furthermore, while they generate hypotheses iteratively, they largely lack the ability to explicitly synthesize their own accumulated findings to uncover complex, interconnected phenomena. We introduce DiscoPER, an autonomous large language model-powered framework that conducts open-ended research by dynamically generating and executing code to explore datasets without pre-specified research objectives. To ensure rigorous scientific validity, every proposed discovery must pass statistical testing. To overcome the limitations of isolated search, our framework introduces a second-order reasoning mechanism that periodically analyzes its own accumulated discoveries. By treating prior discoveries as empirical data, DiscoPER identifies structural patterns, confounds, and epistemic gaps, actively redirecting hypothesis exploration toward uncharted regions of the search space. The search space is further expanded by incorporating tool use, enabling the system to explore hypotheses beyond structured metadata by seamlessly processing and extracting useful information from multimodal sources like images. Evaluated on iNatDisco, a new multimodal ecological knowledge benchmark with pattern-level ground truth obtained from peer-reviewed literature, DiscoPER recovers 8 of 9 known patterns with a 72.7% hypothesis support rate, outperforming both classical causal discovery and LLM-guided baselines. Ablations show that DiscoPER scales with more data, and confirms the benefits of second-order meta-reflection.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_2055cb0993b01708f91942b4